Stars
Fast and Light DensePose implementation
A dataset for 3D hand reconstruction in the wild.
Neural Pose Transfer by Spatially Adaptive Instance Normalization. In CVPR 2020
This work is based on our paper "DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes", which appeared at the IEEE Conference On Computer Vision And Pattern Recognition (CVPR) 2…
High-Resolution 3D Human Digitization from A Single Image.
Reconstruct Watertight Meshes from Point Clouds [SIGGRAPH 2020]
Parsing R-CNN for Instance-Level Human Analysis
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models
Efficient Graph Generation with Graph Recurrent Attention Networks, Deep Generative Model of Graphs, Graph Neural Networks, NeurIPS 2019
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
shreyashampali / ho3d
Forked from lmb-freiburg/freihandA dataset for pose estimation of hand when interacting with object and severe occlusions.
Pytorch reproduction of the paper "Gaussian Mixture Model Convolutional Networks" (CVPR 17)
Pytorch reproduction of the paper "FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis" (CVPR 18)
Pytorch reproduction of the paper "Generating 3D faces using Convolutional Mesh Autoencoders (CoMA)" (ECCV 2018)
Must-read papers on graph neural networks (GNN)
Graph Neural Networks with Keras and Tensorflow 2.
Normalizing flows in PyTorch. Current intended use is education not production.
SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator (ICCV-W 2019)
Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer (NeurIPS 2019)
A PyTorch Library for Accelerating 3D Deep Learning Research
Collection of reinforcement learning algorithms
Repository for the paper "Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop"
A dataset for estimation of hand pose and shape from single color images.
Cross-platform, customizable ML solutions for live and streaming media.
Reinforcement learning environments with musculoskeletal models
Code release for "Canonical Surface Mapping via Geometric Cycle Consistency"