Timezone: »
Geometric Deep Learning has recently made striking progress with the advent of continuous Deep Implicit Fields. They allow for detailed modeling of watertight surfaces of arbitrary topology while not relying on a 3D Euclidean grid, resulting in a learnable parameterization that is not limited in resolution.
Unfortunately, these methods are often not suitable for applications that require an explicit mesh-based surface representation because converting an implicit field to such a representation relies on the Marching Cubes algorithm, which cannot be differentiated with respect to the underlying implicit field.
In this work, we remove this limitation and introduce a differentiable way to produce explicit surface mesh representations from Deep Signed Distance Functions. Our key insight is that by reasoning on how implicit field perturbations impact local surface geometry, one can ultimately differentiate the 3D location of surface samples with respect to the underlying deep implicit field. We exploit this to define MeshSDF, an end-to-end differentiable mesh representation which can vary its topology.
We use two different applications to validate our theoretical insight: Single-View Reconstruction via Differentiable Rendering and Physically-Driven Shape Optimization. In both cases our differentiable parameterization gives us an edge over state-of-the-art algorithms.
Author Information
Edoardo Remelli (EPFL)
Artem Lukoianov (EPFL/NeuralConcept)
Hello! I am a passionate researcher in Computer Vision. Currently, I am getting my Masters's degree in Data Science EPFL, Switzerland, and working part-time as a Machine Learning Researcher, building a system for the fastest Computer Assisted Engineering.
Stephan Richter (Intel Labs)
Benoit Guillard (EPFL)
Timur Bagautdinov (Facebook)
Pierre Baque (Neural Concept SA)
Pascal Fua (EPFL, Switzerland)
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Spotlight: MeshSDF: Differentiable Iso-Surface Extraction »
Tue. Dec 8th 03:00 -- 03:10 PM Room Orals & Spotlights: Deep Learning
More from the Same Authors
-
2021 : SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation »
Robin Chan · Krzysztof Lis · Svenja Uhlemeyer · Hermann Blum · Sina Honari · Roland Siegwart · Pascal Fua · Mathieu Salzmann · Matthias Rottmann -
2023 Poster: ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns »
Ren Li · Benoit Guillard · Pascal Fua -
2021 Poster: Looking Beyond Single Images for Contrastive Semantic Segmentation Learning »
FEIHU ZHANG · Philip Torr · Rene Ranftl · Stephan Richter -
2020 Poster: UCLID-Net: Single View Reconstruction in Object Space »
Benoit Guillard · Edoardo Remelli · Pascal Fua -
2020 Poster: DISK: Learning local features with policy gradient »
Michał Tyszkiewicz · Pascal Fua · Eduard Trulls -
2020 Spotlight: DISK: Learning local features with policy gradient »
Michał Tyszkiewicz · Pascal Fua · Eduard Trulls -
2019 Demonstration: Real Time CFD simulations with 3D Mesh Convolutional Networks »
Pierre Baque · Pascal Fua · François Fleuret -
2019 Poster: Backpropagation-Friendly Eigendecomposition »
Wei Wang · Zheng Dang · Yinlin Hu · Pascal Fua · Mathieu Salzmann -
2018 Poster: LF-Net: Learning Local Features from Images »
Yuki Ono · Eduard Trulls · Pascal Fua · Kwang Moo Yi -
2017 Poster: Learning Active Learning from Data »
Ksenia Konyushkova · Raphael Sznitman · Pascal Fua -
2015 Poster: Kullback-Leibler Proximal Variational Inference »
Mohammad Emtiyaz Khan · Pierre Baque · François Fleuret · Pascal Fua -
2013 Poster: Non-Linear Domain Adaptation with Boosting »
Carlos J Becker · Christos M Christoudias · Pascal Fua