Publication

Shape Reconstruction by Learning Differentiable Surface Representations

Related publications (36)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

Pascal Fua, Mathieu Salzmann, Zheng Dang, Kwang Moo Yi, Fei Wang, Yinlin Hu

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be tackled by solving a linear least-square problem, which can be done by finding the eigenvector corresponding to the smal ...

IEEE COMPUTER SOC2021

The way our brain learns to disentangle complex signals into unambiguous concepts is fascinating but remains largely unknown. There is evidence, however, that hierarchical neural representations play a key role in the cortex. This thesis investigates biolo ...

EPFL2021

Defect segmentation for multi-illumination quality control systems

Pascal Fua, Engin Türetken, Siavash Arjomand Bigdeli, David Honzátko

Thanks to recent advancements in image processing and deep learning techniques, visual surface inspection in production lines has become an automated process as long as all the defects are visible in a single or a few images. However, it is often necessary ...

2021

, , , , , , ,

LiftPose3D infers three-dimensional poses from two-dimensional data or from limited three-dimensional data. The approach is illustrated for videos of behaving Drosophila, mice, rats and macaques. Markerless three-dimensional (3D) pose estimation has become ...

NATURE PORTFOLIO2021

, ,

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness co ...

2021

, , ,

Two distinct limits for deep learning have been derived as the network width h -> infinity, depending on how the weights of the last layer scale with h. In the neural tangent Kernel (NTK) limit, the dynamics becomes linear in the weights and is described b ...

IOP PUBLISHING LTD2020

Tracing in 2D to reduce the annotation effort for 3D deep delineation of linear structures

Pascal Fua, Mathieu Salzmann, Agata Justyna Mosinska, Mateusz Kozinski

The difficulty of obtaining annotations to build training databases still slows down the adoption of recent deep learning approaches for biomedical image analysis. In this paper, we show that we can train a Deep Net to perform 3D volumetric delineation giv ...

ELSEVIER2020

Better Patch Stitching for Parametric Surface Reconstruction

Pascal Fua, Mathieu Salzmann, Zhantao Deng, Jan Bednarík

Recently, parametric mappings have emerged as highly effective surface representations, yielding low reconstruction error. In particular, the latest works represent the target shape as an atlas of multiple mappings, which can closely encode object parts. A ...

IEEE2020

Non-contact polishing of a crystalline layer or substrate by ion beam etching

Niels Quack, Teodoro Graziosi, Sichen Mi

Polishing method comprising the steps of: - providing at least one crystalline layer or substrate, the at least one crystalline layer or substrate extending in at least one plane, and including at least one outer surface and at least one depression extendi ...

2020

GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping

Pascal Fua, Mathieu Salzmann, Victor Constantin, Erhan Gündogdu

While Physics-Based Simulation (PBS) can accurately drape a 3D garment on a 3D body, it remains too costly for real-time applications, such as virtual try-on. By contrast, inference in a deep network, requiring a single forward pass, is much faster. Taking ...

IEEE2019