Tal Remez - Academia.edu (original) (raw)

Papers by Tal Remez

arXiv (Cornell University), Dec 21, 2022

Prior works on improving speech quality with visual input typically study each type of auditory d... more Prior works on improving speech quality with visual input typically study each type of auditory distortion separately (e.g., separation, inpainting, video-to-speech) and present tailored algorithms. This paper proposes to unify these subjects and study Generalized Speech Enhancement, where the goal is not to reconstruct the exact reference clean signal, but to focus on improving certain aspects of speech. In particular, this paper concerns intelligibility, quality, and video synchronization. We cast the problem as audiovisual speech resynthesis, which is composed of two steps: pseudo audiovisual speech recognition (P-AVSR) and pseudo text-to-speech synthesis (P-TTS). P-AVSR and P-TTS are connected by discrete units derived from a self-supervised speech model. Moreover, we utilize self-supervised audiovisual speech model to initialize P-AVSR. The proposed model is coined ReVISE. ReVISE is the first high-quality model for in-the-wild video-to-speech synthesis and achieves superior performance on all LRS3 audiovisual enhancement tasks with a single model. To demonstrates its applicability in the real world, ReVISE is also evaluated on EasyCom, an audiovisual benchmark collected under challenging acoustic conditions with only 1.6 hours of training data. Similarly, ReVISE greatly suppresses noise and improves quality. Project page: https: //wnhsu.github.io/ReVISE.

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

In this paper we present VDTTS, a Visually-Driven Textto-Speech model. Motivated by dubbing, VDTT... more In this paper we present VDTTS, a Visually-Driven Textto-Speech model. Motivated by dubbing, VDTTS takes advantage of video frames as an additional input alongside text, and generates speech that matches the video signal. We demonstrate how this allows VDTTS to, unlike plain TTS models, generate speech that not only has prosodic variations like natural pauses and pitch, but is also synchronized to the input video. Experimentally, we show our model produces wellsynchronized outputs, approaching the video-speech synchronization quality of the ground-truth, on several challenging benchmarks including "in-the-wild" content from VoxCeleb2. We encourage the reader to view the demo videos demonstrating video-speech synchronization, robustness to speaker ID swapping, and prosody.

Cornell University - arXiv, Jul 20, 2022

We introduce AudioScopeV2, a state-of-the-art universal audiovisual on-screen sound separation sy... more We introduce AudioScopeV2, a state-of-the-art universal audiovisual on-screen sound separation system which is capable of learning to separate sounds and associate them with on-screen objects by looking at in-the-wild videos. We identify several limitations of previous work on audiovisual on-screen sound separation, including the coarse resolution of spatio-temporal attention, poor convergence of the audio separation model, limited variety in training and evaluation data, and failure to account for the trade off between preservation of on-screen sounds and suppression of off-screen sounds. We provide solutions to all of these issues. Our proposed cross-modal and self-attention network architectures capture audiovisual dependencies at a finer resolution over time, and we also propose efficient separable variants that are capable of scaling to longer videos without sacrificing much performance. We also find that pre-training the separation model only on audio greatly improves results. For training and evaluation, we collected new human annotations of onscreen sounds from a large database of in-the-wild videos (YFCC100M). This new dataset is more diverse and challenging. Finally, we propose a calibration procedure that allows exact tuning of on-screen reconstruction versus off-screen suppression, which greatly simplifies comparing performance between models with different operating points. Overall, our experimental results show marked improvements in on-screen separation performance under much more general conditions than previous methods with minimal additional computational complexity.

International Conference on Learning Representations, May 3, 2021

Recent progress in deep learning has enabled many advances in sound separation and visual scene u... more Recent progress in deep learning has enabled many advances in sound separation and visual scene understanding. However, extracting sound sources which are apparent in natural videos remains an open problem. In this work, we present AudioScope, a novel audiovisual sound separation framework that can be trained without supervision to isolate on-screen sound sources from real in-the-wild videos. Prior audiovisual separation work assumed artificial limitations on the domain of sound classes (e.g., to speech or music), constrained the number of sources, and required strong sound separation or visual segmentation labels. AudioScope overcomes these limitations, operating on an open domain of sounds, with variable numbers of sources, and without labels or prior visual segmentation. The training procedure for AudioScope uses mixture invariant training (MixIT) to separate synthetic mixtures of mixtures (MoMs) into individual sources, where noisy labels for mixtures are provided by an unsupervised audiovisual coincidence model. Using the noisy labels, along with attention between video and audio features, AudioScope learns to identify audiovisual similarity and to suppress off-screen sounds. We demonstrate the effectiveness of our approach using a dataset of video clips extracted from open-domain YFCC100m video data. This dataset contains a wide diversity of sound classes recorded in unconstrained conditions, making the application of previous methods unsuitable. For evaluation and semi-supervised experiments, we collected human labels for presence of on-screen and off-screen sounds on a small subset of clips. * Work done during an internship at Google.

The registration of surfaces with non-rigid deformation, especially non-isometric deformations, i... more The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences. With the aid of this tiered benchmark of increasingly challenging real scans, we explore this problem and investigate how robust current stateof-the-art methods perform in different challenging registration and correspondence scenarios. We discover that changes in topology is a challenging problem for some methods and that machine learning-based approaches prove to be more capable of handling non-isometric deformations on shapes that are moderately similar to the training set. CCS Concepts • Theory of computation → Computa...

2017 IEEE International Conference on Image Processing (ICIP), 2017

The increasing demand for high image quality in mobile devices brings forth the need for better c... more The increasing demand for high image quality in mobile devices brings forth the need for better computational enhancement techniques, and image denoising in particular. To this end, we propose a new fully convolutional deep neural network architecture which is simple yet powerful and achieves state-of-the-art performance for additive Gaussian noise removal. Furthermore, we claim that the personal photo-collections can usually be categorized into a small set of semantic classes. However simple, this observation has not been exploited in image denoising until now. We show that a significant boost in performance of up to 0.4dB PSNR can be achieved by making our network class-aware, namely, by fine-tuning it for images belonging to a specific semantic class. Relying on the hugely successful existing image classifiers, this research advocates for using a class-aware approach in all image enhancement tasks.

ArXiv, 2017

The increasing demand for high image quality in mobile devices brings forth the need for better c... more The increasing demand for high image quality in mobile devices brings forth the need for better computational enhancement techniques, and image denoising in particular. At the same time, the images captured by these devices can be categorized into a small set of semantic classes. However simple, this observation has not been exploited in image denoising until now. In this paper, we demonstrate how the reconstruction quality improves when a denoiser is aware of the type of content in the image. To this end, we first propose a new fully convolutional deep neural network architecture which is simple yet powerful as it achieves state-of-the-art performance even without being class-aware. We further show that a significant boost in performance of up to 0.40.40.4 dB PSNR can be achieved by making our network class-aware, namely, by fine-tuning it for images belonging to a specific semantic class. Relying on the hugely successful existing image classifiers, this research advocates for using a ...

ArXiv, 2021

We present Translatotron 2, a neural direct speech-to-speech translation model that can be traine... more We present Translatotron 2, a neural direct speech-to-speech translation model that can be trained end-to-end. Translatotron 2 consists of a speech encoder, a phoneme decoder, a mel-spectrogram synthesizer, and an attention module that connects all the previous three components. Experimental results suggest that Translatotron 2 outperforms the original Translatotron by a large margin in terms of translation quality and predicted speech naturalness, and drastically improves the robustness of the predicted speech by mitigating over-generation, such as babbling or long pause. We also propose a new method for retaining the source speaker’s voice in the translated speech. The trained model is restricted to retain the source speaker’s voice, but unlike the original Translatotron, it is not able to generate speech in a different speaker’s voice, making the model more robust for production deployment, by mitigating potential misuse for creating spoofing audio artifacts. When the new method ...

ArXiv, 2016

We present a proof-of-concept end-to-end system for computational extended depth of field (EDOF) ... more We present a proof-of-concept end-to-end system for computational extended depth of field (EDOF) imaging. The acquisition is performed through a phase-coded aperture implemented by placing a thin wavelength-dependent optical mask inside the pupil of a conventional camera lens, as a result of which, each color channel is focused at a different depth. The reconstruction process receives the raw Bayer image as the input, and performs blind estimation of the output color image in focus at an extended range of depths using a patch-wise sparse prior. We present a fast non-iterative reconstruction algorithm operating with constant latency in fixed-point arithmetics and achieving real-time performance in a prototype FPGA implementation. The output of the system, on simulated and real-life scenes, is qualitatively and quantitatively better than the result of clear-aperture imaging followed by state-of-the-art blind deblurring.

ArXiv, 2017

Poisson distribution is used for modeling noise in photon-limited imaging. While canonical exampl... more Poisson distribution is used for modeling noise in photon-limited imaging. While canonical examples include relatively exotic types of sensing like spectral imaging or astronomy, the problem is relevant to regular photography now more than ever due to the booming market for mobile cameras. Restricted form factor limits the amount of absorbed light, thus computational post-processing is called for. In this paper, we make use of the powerful framework of deep convolutional neural networks for Poisson denoising. We demonstrate how by training the same network with images having a specific peak value, our denoiser outperforms previous state-of-the-art by a large margin both visually and quantitatively. Being flexible and data-driven, our solution resolves the heavy ad hoc engineering used in previous methods and is an order of magnitude faster. We further show that by adding a reasonable prior on the class of the image being processed, another significant boost in performance is achieved.

With the development of range sensors such as LIDAR and time-of-flight cameras, 3D point cloud sc... more With the development of range sensors such as LIDAR and time-of-flight cameras, 3D point cloud scans have become ubiquitous in computer vision applications, the most prominent ones being gesture recognition and autonomous driving. Parsimony-based algorithms have shown great success on images and videos where data points are sampled on a regular Cartesian grid. We propose an adaptation of these techniques to irregularly sampled signals by using continuous dictionaries. We present an example application in the form of point cloud denoising.

ArXiv, 2016

With the development of range sensors such as LIDAR and time-of-flight cameras, 3D point cloud sc... more With the development of range sensors such as LIDAR and time-of-flight cameras, 3D point cloud scans have become ubiquitous in computer vision applications, the most prominent ones being gesture recognition and autonomous driving. Parsimony-based algorithms have shown great success on images and videos where data points are sampled on a regular Cartesian grid. We propose an adaptation of these techniques to irregularly sampled signals by using continuous dictionaries. We present an example application in the form of point cloud denoising.

ArXiv, 2015

Recently, the dense binary pixel Gigavision camera had been introduced, emulating a digital versi... more Recently, the dense binary pixel Gigavision camera had been introduced, emulating a digital version of the photographic film. While seems to be a promising solution for HDR imaging, its output is not directly usable and requires an image reconstruction process. In this work, we formulate this problem as the minimization of a convex objective combining a maximum-likelihood term with a sparse synthesis prior. We present MLNet - a novel feed-forward neural network, producing acceptable output quality at a fixed complexity and is two orders of magnitude faster than iterative algorithms. We present state of the art results in the abstract.

Medical Image Computing and Computer Assisted Intervention − MICCAI 2017, 2017

With increasingly sophisticated Diffusion Weighted MRI acquisition methods and modeling technique... more With increasingly sophisticated Diffusion Weighted MRI acquisition methods and modeling techniques, very large sets of streamlines (fibers) are presently generated per imaged brain. These reconstructions of white matter architecture, which are important for human brain research and pre-surgical planning, require a large amount of storage and are often unwieldy and difficult to manipulate and analyze. This work proposes a novel continuous parsimonious framework in which signals are sparsely represented in a dictionary with continuous atoms. The significant innovation in our new methodology is the ability to train such continuous dictionaries, unlike previous approaches that either used pre-fixed continuous transforms or training with finite atoms. This leads to an innovative fiber representation method, which uses Continuous Dictionary Learning to sparsely code each fiber with high accuracy. This method is tested on numerous tractograms produced from the Human Connectome Project data and achieves state-of-the-art performances in compression ratio and reconstruction error.

2017 International Conference on 3D Vision (3DV), 2017

Figure 1: Qualitative examples on FAUST models (left), SHREC'16 (middle) and SCAPE (right). In th... more Figure 1: Qualitative examples on FAUST models (left), SHREC'16 (middle) and SCAPE (right). In the SHREC experiment, the green parts mark where no correspondence was found. Notice how those areas are close to the parts that are hidden in the other model. The missing matches (marked in black) in the SCAPE experiment are an artifact due to the multiscale approach.

2017 IEEE International Conference on Computer Vision (ICCV), 2017

We introduce a new framework for learning dense correspondence between deformable 3D shapes. Exis... more We introduce a new framework for learning dense correspondence between deformable 3D shapes. Existing learning based approaches model shape correspondence as a labelling problem, where each point of a query shape receives a label identifying a point on some reference domain; the correspondence is then constructed a posteriori by composing the label predictions of two input shapes. We propose a paradigm shift and design a structured prediction model in the space of functional maps, linear operators that provide a compact representation of the correspondence. We model the learning process via a deep residual network which takes dense descriptor fields defined on two shapes as input, and outputs a soft map between the two given objects. The resulting correspondence is shown to be accurate on several challenging benchmarks comprising multiple categories, synthetic models, real scans with acquisition artifacts, topological noise, and partiality.

IEEE Transactions on Image Processing, 2018

We propose a fully-convolutional neural-network architecture for image denoising which is simple ... more We propose a fully-convolutional neural-network architecture for image denoising which is simple yet powerful. Its structure allows to exploit the gradual nature of the denoising process, in which shallow layers handle local noise statistics, while deeper layers recover edges and enhance textures. Our method advances the state-of-the-art when trained for different noise levels and distributions (both Gaussian and Poisson). In addition, we show that making the denoiser class-aware by exploiting semantic class information boosts performance, enhances textures and reduces artifacts.

2016 IEEE International Conference on Computational Photography (ICCP), 2016

The pursuit of smaller pixel sizes at ever increasing resolution in digital image sensors is main... more The pursuit of smaller pixel sizes at ever increasing resolution in digital image sensors is mainly driven by the stringent price and form-factor requirements of sensors and optics in the cellular phone market. Recently, Eric Fossum proposed a novel concept of an image sensor with dense sub-diffraction limit one-bit pixels (jots) [6], which can be considered a digital emulation of silver halide photographic film. This idea has been recently embodied as the EPFL Gigavision camera. A major bottleneck in the design of such sensors is the image reconstruction process, producing a continuous high dynamic range image from oversampled binary measurements. The extreme quantization of the Poisson statistics is incompatible with the assumptions of most standard image processing and enhancement frameworks. The recently proposed maximum-likelihood (ML) approach addresses this difficulty, but suffers from image artifacts and has impractically high computational complexity. In this work, we study a variant of a sensor with binary threshold pixels and propose a reconstruction algorithm combining an ML data fitting term with a sparse synthesis prior. We also show an efficient hardware-friendly real-time approximation of this inverse operator. Promising results are shown on synthetic data as well as on HDR data emulated using multiple exposures of a regular CMOS sensor.

Computer Vision and Image Understanding, 2017

We present ASIST, a technique for transforming point clouds by replacing objects with their seman... more We present ASIST, a technique for transforming point clouds by replacing objects with their semantically equivalent counterparts. Transformations of this kind have applications in virtual reality, repair of fused scans, and robotics. ASIST is based on a unified formulation of semantic labeling and object replacement; both result from minimizing a single objective. We present numerical tools for the efficient solution of this optimization problem. The method is experimentally assessed on new datasets of both synthetic and real point clouds, and is additionally compared to two recent works on object replacement on data from the corresponding papers.

ArXiv, 2021

We introduce a state-of-the-art audio-visual on-screen sound separation system which is capable o... more We introduce a state-of-the-art audio-visual on-screen sound separation system which is capable of learning to separate sounds and associate them with on-screen objects by looking at in-the-wild videos. We identify limitations of previous work on audiovisual on-screen sound separation, including the simplicity and coarse resolution of spatio-temporal attention, and poor convergence of the audio separation model. Our proposed model addresses these issues using cross-modal and self-attention modules that capture audio-visual dependencies at a finer resolution over time, and by unsupervised pre-training of audio separation model. These improvements allow the model to generalize to a much wider set of unseen videos. For evaluation and semi-supervised training, we collected human annotations of on-screen audio from a large database of in-the-wild videos (YFCC100M). Our results show marked improvements in on-screen separation performance, in more general conditions than previous methods.

arXiv (Cornell University), Dec 21, 2022

Prior works on improving speech quality with visual input typically study each type of auditory d... more Prior works on improving speech quality with visual input typically study each type of auditory distortion separately (e.g., separation, inpainting, video-to-speech) and present tailored algorithms. This paper proposes to unify these subjects and study Generalized Speech Enhancement, where the goal is not to reconstruct the exact reference clean signal, but to focus on improving certain aspects of speech. In particular, this paper concerns intelligibility, quality, and video synchronization. We cast the problem as audiovisual speech resynthesis, which is composed of two steps: pseudo audiovisual speech recognition (P-AVSR) and pseudo text-to-speech synthesis (P-TTS). P-AVSR and P-TTS are connected by discrete units derived from a self-supervised speech model. Moreover, we utilize self-supervised audiovisual speech model to initialize P-AVSR. The proposed model is coined ReVISE. ReVISE is the first high-quality model for in-the-wild video-to-speech synthesis and achieves superior performance on all LRS3 audiovisual enhancement tasks with a single model. To demonstrates its applicability in the real world, ReVISE is also evaluated on EasyCom, an audiovisual benchmark collected under challenging acoustic conditions with only 1.6 hours of training data. Similarly, ReVISE greatly suppresses noise and improves quality. Project page: https: //wnhsu.github.io/ReVISE.

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

In this paper we present VDTTS, a Visually-Driven Textto-Speech model. Motivated by dubbing, VDTT... more In this paper we present VDTTS, a Visually-Driven Textto-Speech model. Motivated by dubbing, VDTTS takes advantage of video frames as an additional input alongside text, and generates speech that matches the video signal. We demonstrate how this allows VDTTS to, unlike plain TTS models, generate speech that not only has prosodic variations like natural pauses and pitch, but is also synchronized to the input video. Experimentally, we show our model produces wellsynchronized outputs, approaching the video-speech synchronization quality of the ground-truth, on several challenging benchmarks including "in-the-wild" content from VoxCeleb2. We encourage the reader to view the demo videos demonstrating video-speech synchronization, robustness to speaker ID swapping, and prosody.

Cornell University - arXiv, Jul 20, 2022

We introduce AudioScopeV2, a state-of-the-art universal audiovisual on-screen sound separation sy... more We introduce AudioScopeV2, a state-of-the-art universal audiovisual on-screen sound separation system which is capable of learning to separate sounds and associate them with on-screen objects by looking at in-the-wild videos. We identify several limitations of previous work on audiovisual on-screen sound separation, including the coarse resolution of spatio-temporal attention, poor convergence of the audio separation model, limited variety in training and evaluation data, and failure to account for the trade off between preservation of on-screen sounds and suppression of off-screen sounds. We provide solutions to all of these issues. Our proposed cross-modal and self-attention network architectures capture audiovisual dependencies at a finer resolution over time, and we also propose efficient separable variants that are capable of scaling to longer videos without sacrificing much performance. We also find that pre-training the separation model only on audio greatly improves results. For training and evaluation, we collected new human annotations of onscreen sounds from a large database of in-the-wild videos (YFCC100M). This new dataset is more diverse and challenging. Finally, we propose a calibration procedure that allows exact tuning of on-screen reconstruction versus off-screen suppression, which greatly simplifies comparing performance between models with different operating points. Overall, our experimental results show marked improvements in on-screen separation performance under much more general conditions than previous methods with minimal additional computational complexity.

International Conference on Learning Representations, May 3, 2021

Recent progress in deep learning has enabled many advances in sound separation and visual scene u... more Recent progress in deep learning has enabled many advances in sound separation and visual scene understanding. However, extracting sound sources which are apparent in natural videos remains an open problem. In this work, we present AudioScope, a novel audiovisual sound separation framework that can be trained without supervision to isolate on-screen sound sources from real in-the-wild videos. Prior audiovisual separation work assumed artificial limitations on the domain of sound classes (e.g., to speech or music), constrained the number of sources, and required strong sound separation or visual segmentation labels. AudioScope overcomes these limitations, operating on an open domain of sounds, with variable numbers of sources, and without labels or prior visual segmentation. The training procedure for AudioScope uses mixture invariant training (MixIT) to separate synthetic mixtures of mixtures (MoMs) into individual sources, where noisy labels for mixtures are provided by an unsupervised audiovisual coincidence model. Using the noisy labels, along with attention between video and audio features, AudioScope learns to identify audiovisual similarity and to suppress off-screen sounds. We demonstrate the effectiveness of our approach using a dataset of video clips extracted from open-domain YFCC100m video data. This dataset contains a wide diversity of sound classes recorded in unconstrained conditions, making the application of previous methods unsuitable. For evaluation and semi-supervised experiments, we collected human labels for presence of on-screen and off-screen sounds on a small subset of clips. * Work done during an internship at Google.

The registration of surfaces with non-rigid deformation, especially non-isometric deformations, i... more The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences. With the aid of this tiered benchmark of increasingly challenging real scans, we explore this problem and investigate how robust current stateof-the-art methods perform in different challenging registration and correspondence scenarios. We discover that changes in topology is a challenging problem for some methods and that machine learning-based approaches prove to be more capable of handling non-isometric deformations on shapes that are moderately similar to the training set. CCS Concepts • Theory of computation → Computa...

2017 IEEE International Conference on Image Processing (ICIP), 2017

The increasing demand for high image quality in mobile devices brings forth the need for better c... more The increasing demand for high image quality in mobile devices brings forth the need for better computational enhancement techniques, and image denoising in particular. To this end, we propose a new fully convolutional deep neural network architecture which is simple yet powerful and achieves state-of-the-art performance for additive Gaussian noise removal. Furthermore, we claim that the personal photo-collections can usually be categorized into a small set of semantic classes. However simple, this observation has not been exploited in image denoising until now. We show that a significant boost in performance of up to 0.4dB PSNR can be achieved by making our network class-aware, namely, by fine-tuning it for images belonging to a specific semantic class. Relying on the hugely successful existing image classifiers, this research advocates for using a class-aware approach in all image enhancement tasks.

ArXiv, 2017

The increasing demand for high image quality in mobile devices brings forth the need for better c... more The increasing demand for high image quality in mobile devices brings forth the need for better computational enhancement techniques, and image denoising in particular. At the same time, the images captured by these devices can be categorized into a small set of semantic classes. However simple, this observation has not been exploited in image denoising until now. In this paper, we demonstrate how the reconstruction quality improves when a denoiser is aware of the type of content in the image. To this end, we first propose a new fully convolutional deep neural network architecture which is simple yet powerful as it achieves state-of-the-art performance even without being class-aware. We further show that a significant boost in performance of up to 0.40.40.4 dB PSNR can be achieved by making our network class-aware, namely, by fine-tuning it for images belonging to a specific semantic class. Relying on the hugely successful existing image classifiers, this research advocates for using a ...

ArXiv, 2021

We present Translatotron 2, a neural direct speech-to-speech translation model that can be traine... more We present Translatotron 2, a neural direct speech-to-speech translation model that can be trained end-to-end. Translatotron 2 consists of a speech encoder, a phoneme decoder, a mel-spectrogram synthesizer, and an attention module that connects all the previous three components. Experimental results suggest that Translatotron 2 outperforms the original Translatotron by a large margin in terms of translation quality and predicted speech naturalness, and drastically improves the robustness of the predicted speech by mitigating over-generation, such as babbling or long pause. We also propose a new method for retaining the source speaker’s voice in the translated speech. The trained model is restricted to retain the source speaker’s voice, but unlike the original Translatotron, it is not able to generate speech in a different speaker’s voice, making the model more robust for production deployment, by mitigating potential misuse for creating spoofing audio artifacts. When the new method ...

ArXiv, 2016

We present a proof-of-concept end-to-end system for computational extended depth of field (EDOF) ... more We present a proof-of-concept end-to-end system for computational extended depth of field (EDOF) imaging. The acquisition is performed through a phase-coded aperture implemented by placing a thin wavelength-dependent optical mask inside the pupil of a conventional camera lens, as a result of which, each color channel is focused at a different depth. The reconstruction process receives the raw Bayer image as the input, and performs blind estimation of the output color image in focus at an extended range of depths using a patch-wise sparse prior. We present a fast non-iterative reconstruction algorithm operating with constant latency in fixed-point arithmetics and achieving real-time performance in a prototype FPGA implementation. The output of the system, on simulated and real-life scenes, is qualitatively and quantitatively better than the result of clear-aperture imaging followed by state-of-the-art blind deblurring.

ArXiv, 2017

Poisson distribution is used for modeling noise in photon-limited imaging. While canonical exampl... more Poisson distribution is used for modeling noise in photon-limited imaging. While canonical examples include relatively exotic types of sensing like spectral imaging or astronomy, the problem is relevant to regular photography now more than ever due to the booming market for mobile cameras. Restricted form factor limits the amount of absorbed light, thus computational post-processing is called for. In this paper, we make use of the powerful framework of deep convolutional neural networks for Poisson denoising. We demonstrate how by training the same network with images having a specific peak value, our denoiser outperforms previous state-of-the-art by a large margin both visually and quantitatively. Being flexible and data-driven, our solution resolves the heavy ad hoc engineering used in previous methods and is an order of magnitude faster. We further show that by adding a reasonable prior on the class of the image being processed, another significant boost in performance is achieved.

With the development of range sensors such as LIDAR and time-of-flight cameras, 3D point cloud sc... more With the development of range sensors such as LIDAR and time-of-flight cameras, 3D point cloud scans have become ubiquitous in computer vision applications, the most prominent ones being gesture recognition and autonomous driving. Parsimony-based algorithms have shown great success on images and videos where data points are sampled on a regular Cartesian grid. We propose an adaptation of these techniques to irregularly sampled signals by using continuous dictionaries. We present an example application in the form of point cloud denoising.

ArXiv, 2016

With the development of range sensors such as LIDAR and time-of-flight cameras, 3D point cloud sc... more With the development of range sensors such as LIDAR and time-of-flight cameras, 3D point cloud scans have become ubiquitous in computer vision applications, the most prominent ones being gesture recognition and autonomous driving. Parsimony-based algorithms have shown great success on images and videos where data points are sampled on a regular Cartesian grid. We propose an adaptation of these techniques to irregularly sampled signals by using continuous dictionaries. We present an example application in the form of point cloud denoising.

ArXiv, 2015

Recently, the dense binary pixel Gigavision camera had been introduced, emulating a digital versi... more Recently, the dense binary pixel Gigavision camera had been introduced, emulating a digital version of the photographic film. While seems to be a promising solution for HDR imaging, its output is not directly usable and requires an image reconstruction process. In this work, we formulate this problem as the minimization of a convex objective combining a maximum-likelihood term with a sparse synthesis prior. We present MLNet - a novel feed-forward neural network, producing acceptable output quality at a fixed complexity and is two orders of magnitude faster than iterative algorithms. We present state of the art results in the abstract.

Medical Image Computing and Computer Assisted Intervention − MICCAI 2017, 2017

With increasingly sophisticated Diffusion Weighted MRI acquisition methods and modeling technique... more With increasingly sophisticated Diffusion Weighted MRI acquisition methods and modeling techniques, very large sets of streamlines (fibers) are presently generated per imaged brain. These reconstructions of white matter architecture, which are important for human brain research and pre-surgical planning, require a large amount of storage and are often unwieldy and difficult to manipulate and analyze. This work proposes a novel continuous parsimonious framework in which signals are sparsely represented in a dictionary with continuous atoms. The significant innovation in our new methodology is the ability to train such continuous dictionaries, unlike previous approaches that either used pre-fixed continuous transforms or training with finite atoms. This leads to an innovative fiber representation method, which uses Continuous Dictionary Learning to sparsely code each fiber with high accuracy. This method is tested on numerous tractograms produced from the Human Connectome Project data and achieves state-of-the-art performances in compression ratio and reconstruction error.

2017 International Conference on 3D Vision (3DV), 2017

Figure 1: Qualitative examples on FAUST models (left), SHREC'16 (middle) and SCAPE (right). In th... more Figure 1: Qualitative examples on FAUST models (left), SHREC'16 (middle) and SCAPE (right). In the SHREC experiment, the green parts mark where no correspondence was found. Notice how those areas are close to the parts that are hidden in the other model. The missing matches (marked in black) in the SCAPE experiment are an artifact due to the multiscale approach.

2017 IEEE International Conference on Computer Vision (ICCV), 2017

We introduce a new framework for learning dense correspondence between deformable 3D shapes. Exis... more We introduce a new framework for learning dense correspondence between deformable 3D shapes. Existing learning based approaches model shape correspondence as a labelling problem, where each point of a query shape receives a label identifying a point on some reference domain; the correspondence is then constructed a posteriori by composing the label predictions of two input shapes. We propose a paradigm shift and design a structured prediction model in the space of functional maps, linear operators that provide a compact representation of the correspondence. We model the learning process via a deep residual network which takes dense descriptor fields defined on two shapes as input, and outputs a soft map between the two given objects. The resulting correspondence is shown to be accurate on several challenging benchmarks comprising multiple categories, synthetic models, real scans with acquisition artifacts, topological noise, and partiality.

IEEE Transactions on Image Processing, 2018

We propose a fully-convolutional neural-network architecture for image denoising which is simple ... more We propose a fully-convolutional neural-network architecture for image denoising which is simple yet powerful. Its structure allows to exploit the gradual nature of the denoising process, in which shallow layers handle local noise statistics, while deeper layers recover edges and enhance textures. Our method advances the state-of-the-art when trained for different noise levels and distributions (both Gaussian and Poisson). In addition, we show that making the denoiser class-aware by exploiting semantic class information boosts performance, enhances textures and reduces artifacts.

2016 IEEE International Conference on Computational Photography (ICCP), 2016

The pursuit of smaller pixel sizes at ever increasing resolution in digital image sensors is main... more The pursuit of smaller pixel sizes at ever increasing resolution in digital image sensors is mainly driven by the stringent price and form-factor requirements of sensors and optics in the cellular phone market. Recently, Eric Fossum proposed a novel concept of an image sensor with dense sub-diffraction limit one-bit pixels (jots) [6], which can be considered a digital emulation of silver halide photographic film. This idea has been recently embodied as the EPFL Gigavision camera. A major bottleneck in the design of such sensors is the image reconstruction process, producing a continuous high dynamic range image from oversampled binary measurements. The extreme quantization of the Poisson statistics is incompatible with the assumptions of most standard image processing and enhancement frameworks. The recently proposed maximum-likelihood (ML) approach addresses this difficulty, but suffers from image artifacts and has impractically high computational complexity. In this work, we study a variant of a sensor with binary threshold pixels and propose a reconstruction algorithm combining an ML data fitting term with a sparse synthesis prior. We also show an efficient hardware-friendly real-time approximation of this inverse operator. Promising results are shown on synthetic data as well as on HDR data emulated using multiple exposures of a regular CMOS sensor.

Computer Vision and Image Understanding, 2017

We present ASIST, a technique for transforming point clouds by replacing objects with their seman... more We present ASIST, a technique for transforming point clouds by replacing objects with their semantically equivalent counterparts. Transformations of this kind have applications in virtual reality, repair of fused scans, and robotics. ASIST is based on a unified formulation of semantic labeling and object replacement; both result from minimizing a single objective. We present numerical tools for the efficient solution of this optimization problem. The method is experimentally assessed on new datasets of both synthetic and real point clouds, and is additionally compared to two recent works on object replacement on data from the corresponding papers.

ArXiv, 2021

We introduce a state-of-the-art audio-visual on-screen sound separation system which is capable o... more We introduce a state-of-the-art audio-visual on-screen sound separation system which is capable of learning to separate sounds and associate them with on-screen objects by looking at in-the-wild videos. We identify limitations of previous work on audiovisual on-screen sound separation, including the simplicity and coarse resolution of spatio-temporal attention, and poor convergence of the audio separation model. Our proposed model addresses these issues using cross-modal and self-attention modules that capture audio-visual dependencies at a finer resolution over time, and by unsupervised pre-training of audio separation model. These improvements allow the model to generalize to a much wider set of unseen videos. For evaluation and semi-supervised training, we collected human annotations of on-screen audio from a large database of in-the-wild videos (YFCC100M). Our results show marked improvements in on-screen separation performance, in more general conditions than previous methods.