Open AccessProceedings Article
GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
Edward J. Smith,Scott Fujimoto,Adriana Romero,David Meger +3 more
- pp 5866-5876
TLDR
In this paper, a graph convolutional update preserving vertex information and an adaptive splitting heuristic allowing detail to emerge is proposed for 3D object reconstruction from images with the ShapeNet dataset.Abstract:
Mesh models are a promising approach for encoding the structure of 3D objects. Current mesh reconstruction systems predict uniformly distributed vertex locations of a predetermined graph through a series of graph convolutions, leading to compromises with respect to performance or resolution. In this paper, we argue that the graph representation of geometric objects allows for additional structure, which should be leveraged for enhanced reconstruction. Thus, we propose a system which properly benefits from the advantages of the geometric structure of graph encoded objects by introducing (1) a graph convolutional update preserving vertex information; (2) an adaptive splitting heuristic allowing detail to emerge; and (3) a training objective operating both on the local surfaces defined by vertices as well as the global structure defined by the mesh. Our proposed method is evaluated on the task of 3D object reconstruction from images with the ShapeNet dataset, where we demonstrate state of the art performance, both visually and numerically, while having far smaller space requirements by generating adaptive meshesread more
Citations
More filters
Posted Content
Accelerating 3D Deep Learning with PyTorch3D
Nikhila Ravi,Jeremy Reizenstein,David Novotny,Taylor Gordon,Wan-Yen Lo,Justin Johnson,Georgia Gkioxari +6 more
TL;DR: 1. Accelerating 3D Deep Learning with PyTorch3D, arXiv 2007 2. Mesh R-CNN, ICCV 2019 3. SynSin: End-to-end View Synthesis from a Single Image, CVPR 2020 4. Fast Differentiable Raycasting for Neural Rendering using Sphere-based Representations.
Proceedings ArticleDOI
Local Deep Implicit Functions for 3D Shape
TL;DR: Local Deep Implicit Functions (LDIF), a 3D shape representation that decomposes space into a structured set of learned implicit functions that provides higher surface reconstruction accuracy than the state-of-the-art (OccNet), while requiring fewer than 1\% of the network parameters.
Proceedings ArticleDOI
Mesh R-CNN
TL;DR: Mesh R-CNN as discussed by the authors proposes a mesh prediction branch that outputs meshes with varying topological structure by first predicting coarse voxel representations which are converted to meshes and refined with a graph convolution network operating over the mesh's vertices and edges.
Proceedings ArticleDOI
Learning to Dress 3D People in Generative Clothing
Qianli Ma,Jinlong Yang,Anurag Ranjan,Sergi Pujades,Gerard Pons-Moll,Siyu Tang,Michael J. Black +6 more
TL;DR: This work learns a generative 3D mesh model of clothed people from 3D scans with varying pose and clothing, and is the first generative model that directly dresses 3D human body meshes and generalizes to different poses.
Posted Content
Mesh R-CNN
TL;DR: This work proposes a system that detects objects in real-world images and produces a triangle mesh giving the full 3D shape of each detected object, augments Mask R-CNN with a mesh prediction branch that outputs meshes with varying topological structure.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Proceedings Article
Auto-Encoding Variational Bayes
Diederik P. Kingma,Max Welling +1 more
TL;DR: A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
Posted Content
Semi-Supervised Classification with Graph Convolutional Networks
Thomas Kipf,Max Welling +1 more
TL;DR: A scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs which outperforms related methods by a significant margin.
Proceedings Article
Rectified Linear Units Improve Restricted Boltzmann Machines
Vinod Nair,Geoffrey E. Hinton +1 more
TL;DR: Restricted Boltzmann machines were developed using binary stochastic hidden units that learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset.