The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

Deformable ConvNets V2 (DCNv2) in PyTorch

Efficient GPU kernels for block-sparse matrix multiplication and convolution

GA-Net: Guided Aggregation Net for End-to-end Stereo Matching

Distribution-Aware Coordinate Representation for Human Pose Estimation

Integral Human Pose Regression

PyTorch implementation of Deformable Convolution

Official pytorch Code for CVPR2019 paper "Fast Human Pose Estimation" https://arxiv.org/abs/1811.05419

Approximate nearest neighbor search with product quantization on GPU in pytorch and cuda

Deforming kernels to adapt towards object deformation. In ICLR 2020.

Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade