Recovery of superquadric parameters from range images using deep learning (original) (raw)
2019
With the recent advancements in deep neural computation, we devise a method to recover superquadric parameters from range images using a convolutional neural network. By training our simple, fullyconvolutional architecture on synthetic data images, containing a single superquadric, we achieve encouraging results. In a fixed rotation scenario, the model could already be used in practice, but we still need to improve on prediction of arbitrary rotational parameters in the future
Related papers
Segmentation and Recovery of Superquadric Models using Convolutional Neural Networks
2020
In this paper we address the problem of representing 3D visual data with parameterized volumetric shape primitives. Specifically, we present a (two-stage) approach built around convolutional neural networks (CNNs) capable of segmenting complex depth scenes into the simpler geometric structures that can be represented with superquadric models. In the first stage, our approach uses a Mask RCNN model to identify superquadric-like structures in depth scenes and then fits superquadric models to the segmented structures using a specially designed CNN regressor. Using our approach we are able to describe complex structures with a small number of interpretable parameters. We evaluated the proposed approach on synthetic as well as real-world depth data and show that our solution does not only result in competitive performance in comparison to the state-of-the-art, but is able to decompose scenes into a number of superquadric models at a fraction of the time required by competing approaches. ...
A multilayer feedforward network for model estimation from range data
2002
A novel neural architecture aimed to estimate superquadrics parameters form range data is presented. The network topology is designed to model and compute the inside-outside function of an undeformed superquadric in whatever attitude, starting from the (x, y, z) data triples. The network has been trained using backpropagation, and the weights arrangement, after training, represents a robust estimate of the superquadric parameters. The architectural approach is general, it can be extended to other geometric primitives for ...
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.