Mark Boss - Academia.edu (original) (raw)

Papers by Mark Boss

Scientific Reports

Substandard and falsified medicines present a serious threat to public health. Simple, low-cost s... more Substandard and falsified medicines present a serious threat to public health. Simple, low-cost screening tools are important in the identification of such products in low- and middle-income countries. In the present study, a smartphone-based imaging software was developed for the quantification of thin-layer chromatographic (TLC) analyses. A performance evaluation of this tool in the TLC analysis of 14 active pharmaceutical ingredients according to the procedures of the Global Pharma Health Fund (GPHF) Minilab was carried out, following international guidelines and assessing accuracy, repeatability, intermediate precision, specificity, linearity, range and robustness of the method. Relative standard deviations of 2.79% and 4.46% between individual measurements were observed in the assessments of repeatability and intermediate precision, respectively. Small deliberate variations of the conditions hardly affected the results. A locally producible wooden box was designed which ensures...

Implementation details. The main network Nθ1 /Nφ1 uses 8 MLP layers with a feature dimension of 2... more Implementation details. The main network Nθ1 /Nφ1 uses 8 MLP layers with a feature dimension of 256 and ReLU activation. The input coordinate x is transformed by the Fourier output γ(x) with 10 bands to 63 features. For the sampling network, the output from the main network is then transformed to the density σ with a single MLP layer without any activation. The flattened 192 SGs parameters Γ are compacted to 16 features using a fully connected layer (Nθ2 ) without any activation. As the value range can be large in the real-world illuminations, the amplitudes α are normalized to [0, 1]. The main network output is then concatenated with the SGs embeddings and passed to the final prediction network. Here, an MLP with ReLU activation is first reducing the joined input to 128 features. The final color prediction c is handled in the last layer without activation and an output dimension of 3. The decomposition network uses the output from Nφ1 and directly predicts the direct color d and th...

2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021

Google Research Basecolor Metallic Roughness Normal Multi-View Images NeRD Volume Decomposed BRDF... more Google Research Basecolor Metallic Roughness Normal Multi-View Images NeRD Volume Decomposed BRDF Relighting & View synthesis Textured Mesh Figure 1: Neural Reflectance Decomposition for Relighting. We encode multiple views of an object under varying or fixed illumination into the NeRD volume. We decompose each given image into geometry, spatially-varying BRDF parameters and a rough approximation of the incident illumination in a globally consistent manner. We then extract a relightable textured mesh that can be re-rendered under novel illumination conditions in real-time.

Decomposing a scene into its shape, reflectance and illumination is a fundamental problem in comp... more Decomposing a scene into its shape, reflectance and illumination is a fundamental problem in computer vision and graphics. Neural approaches such as NeRF have achieved remarkable success in view synthesis, but do not explicitly perform decomposition and instead operate exclusively on radiance (the product of reflectance and illumination). Extensions to NeRF, such as NeRD, can perform decomposition but struggle to accurately recover detailed illumination, thereby significantly limiting realism. We propose a novel reflectance decomposition network that can estimate shape, BRDF and per-image illumination given a set of object images captured under varying illumination. Our key technique is a novel illumination integration network called Neural-PIL that replaces a costly illumination integral operation in the rendering with a simple network query. In addition, we also learn deep low-dimensional priors on BRDF and illumination representations using novel smooth manifold auto-encoders. Ou...

ArXiv, 2019

Creating plausible surfaces is an essential component in achieving a high degree of realism in re... more Creating plausible surfaces is an essential component in achieving a high degree of realism in rendering. To relieve artists, who create these surfaces in a time-consuming, manual process, automated retrieval of the spatially-varying Bidirectional Reflectance Distribution Function (SVBRDF) from a single mobile phone image is desirable. By leveraging a deep neural network, this casual capturing method can be achieved. The trained network can estimate per pixel normal, base color, metallic and roughness parameters from the Disney BRDF. The input image is taken with a mobile phone lit by the camera flash. The network is trained to compensate for environment lighting and thus learned to reduce artifacts introduced by other light sources. These losses contain a multi-scale discriminator with an additional perceptual loss, a rendering loss using a differentiable renderer, and a parameter loss. Besides the local precision, this loss formulation generates material texture maps which are glo...

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020

Flash No-Flash Mask Novel Re-render Diffuse Specular Roughness Normal Depth Figure 1: Practical S... more Flash No-Flash Mask Novel Re-render Diffuse Specular Roughness Normal Depth Figure 1: Practical SVBRDF and shape estimation. Sample two-shot input and the corresponding estimates for SVBRDF (albedo, specularity, roughness) and shape (depth and normals). The novel re-render are animated and show a moving view and light. We recommend Adobe Acrobat or Okular for viewing. Samples are taken from [5].

Surface parameter estimation is an essential field in computer games and movies. An exact represe... more Surface parameter estimation is an essential field in computer games and movies. An exact representation of a real-world surface allows for a higher degree of realism. Capturing or artistically creating these materials is a time-consuming process. We propose a method which utilizes an encoder-decoder Convolutional Neural Network (CNN) to extract parameters for the Bidirectional Reflectance Distribution Function (BRDF) automatically from a sparse sample set. This is done by implementing a differentiable renderer, which allows for a loss backpropagation of rendered images. This photometric loss is essential because defining a numerical BRDF distance metric is difficult. A second loss is added, which compares the parameters maps directly. Therefore, the statistical properties of the BRDF model are learned, which reduces artifacts in the predicted parameters. This dual loss principal improves the result of the network significantly. Opposed to previous means this method retrieves information of the whole surface as spatially varying BRDF (SVBRDF) parameters with a sufficiently high resolution for intended real-world usage. The capture process for materials only requires five known light positions with a fixed camera position. This reduces the scanning time drastically, and a material sample can be obtained in seconds with an automated system.

Scientific Reports

Substandard and falsified medicines present a serious threat to public health. Simple, low-cost s... more Substandard and falsified medicines present a serious threat to public health. Simple, low-cost screening tools are important in the identification of such products in low- and middle-income countries. In the present study, a smartphone-based imaging software was developed for the quantification of thin-layer chromatographic (TLC) analyses. A performance evaluation of this tool in the TLC analysis of 14 active pharmaceutical ingredients according to the procedures of the Global Pharma Health Fund (GPHF) Minilab was carried out, following international guidelines and assessing accuracy, repeatability, intermediate precision, specificity, linearity, range and robustness of the method. Relative standard deviations of 2.79% and 4.46% between individual measurements were observed in the assessments of repeatability and intermediate precision, respectively. Small deliberate variations of the conditions hardly affected the results. A locally producible wooden box was designed which ensures...

Implementation details. The main network Nθ1 /Nφ1 uses 8 MLP layers with a feature dimension of 2... more Implementation details. The main network Nθ1 /Nφ1 uses 8 MLP layers with a feature dimension of 256 and ReLU activation. The input coordinate x is transformed by the Fourier output γ(x) with 10 bands to 63 features. For the sampling network, the output from the main network is then transformed to the density σ with a single MLP layer without any activation. The flattened 192 SGs parameters Γ are compacted to 16 features using a fully connected layer (Nθ2 ) without any activation. As the value range can be large in the real-world illuminations, the amplitudes α are normalized to [0, 1]. The main network output is then concatenated with the SGs embeddings and passed to the final prediction network. Here, an MLP with ReLU activation is first reducing the joined input to 128 features. The final color prediction c is handled in the last layer without activation and an output dimension of 3. The decomposition network uses the output from Nφ1 and directly predicts the direct color d and th...

2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021

Google Research Basecolor Metallic Roughness Normal Multi-View Images NeRD Volume Decomposed BRDF... more Google Research Basecolor Metallic Roughness Normal Multi-View Images NeRD Volume Decomposed BRDF Relighting & View synthesis Textured Mesh Figure 1: Neural Reflectance Decomposition for Relighting. We encode multiple views of an object under varying or fixed illumination into the NeRD volume. We decompose each given image into geometry, spatially-varying BRDF parameters and a rough approximation of the incident illumination in a globally consistent manner. We then extract a relightable textured mesh that can be re-rendered under novel illumination conditions in real-time.

Decomposing a scene into its shape, reflectance and illumination is a fundamental problem in comp... more Decomposing a scene into its shape, reflectance and illumination is a fundamental problem in computer vision and graphics. Neural approaches such as NeRF have achieved remarkable success in view synthesis, but do not explicitly perform decomposition and instead operate exclusively on radiance (the product of reflectance and illumination). Extensions to NeRF, such as NeRD, can perform decomposition but struggle to accurately recover detailed illumination, thereby significantly limiting realism. We propose a novel reflectance decomposition network that can estimate shape, BRDF and per-image illumination given a set of object images captured under varying illumination. Our key technique is a novel illumination integration network called Neural-PIL that replaces a costly illumination integral operation in the rendering with a simple network query. In addition, we also learn deep low-dimensional priors on BRDF and illumination representations using novel smooth manifold auto-encoders. Ou...

ArXiv, 2019

Creating plausible surfaces is an essential component in achieving a high degree of realism in re... more Creating plausible surfaces is an essential component in achieving a high degree of realism in rendering. To relieve artists, who create these surfaces in a time-consuming, manual process, automated retrieval of the spatially-varying Bidirectional Reflectance Distribution Function (SVBRDF) from a single mobile phone image is desirable. By leveraging a deep neural network, this casual capturing method can be achieved. The trained network can estimate per pixel normal, base color, metallic and roughness parameters from the Disney BRDF. The input image is taken with a mobile phone lit by the camera flash. The network is trained to compensate for environment lighting and thus learned to reduce artifacts introduced by other light sources. These losses contain a multi-scale discriminator with an additional perceptual loss, a rendering loss using a differentiable renderer, and a parameter loss. Besides the local precision, this loss formulation generates material texture maps which are glo...

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020

Flash No-Flash Mask Novel Re-render Diffuse Specular Roughness Normal Depth Figure 1: Practical S... more Flash No-Flash Mask Novel Re-render Diffuse Specular Roughness Normal Depth Figure 1: Practical SVBRDF and shape estimation. Sample two-shot input and the corresponding estimates for SVBRDF (albedo, specularity, roughness) and shape (depth and normals). The novel re-render are animated and show a moving view and light. We recommend Adobe Acrobat or Okular for viewing. Samples are taken from [5].

Surface parameter estimation is an essential field in computer games and movies. An exact represe... more Surface parameter estimation is an essential field in computer games and movies. An exact representation of a real-world surface allows for a higher degree of realism. Capturing or artistically creating these materials is a time-consuming process. We propose a method which utilizes an encoder-decoder Convolutional Neural Network (CNN) to extract parameters for the Bidirectional Reflectance Distribution Function (BRDF) automatically from a sparse sample set. This is done by implementing a differentiable renderer, which allows for a loss backpropagation of rendered images. This photometric loss is essential because defining a numerical BRDF distance metric is difficult. A second loss is added, which compares the parameters maps directly. Therefore, the statistical properties of the BRDF model are learned, which reduces artifacts in the predicted parameters. This dual loss principal improves the result of the network significantly. Opposed to previous means this method retrieves information of the whole surface as spatially varying BRDF (SVBRDF) parameters with a sufficiently high resolution for intended real-world usage. The capture process for materials only requires five known light positions with a fixed camera position. This reduces the scanning time drastically, and a material sample can be obtained in seconds with an automated system.