Transformer-Mamba Diffusion Models

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person

About Project Page for Outfit Anyone

Official Implementation of ICML 2023 paper: "A Generalization of ViT/MLP-Mixer to Graphs"

MPI-IS Mesh Processing Library

Accessible large language models via k-bit quantization for PyTorch.

About Code release for "Flowformer: Linearizing Transformers with Conservation Flows" (ICML 2022), https://arxiv.org/pdf/2202.06258.pdf

Visual Alignment Constraint for Continuous Sign Language Recognition. ( ICCV 2021)

Ongoing research training transformer models at scale

Code release for ConvNeXt model

This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.

Production First and Production Ready End-to-End Speech Recognition Toolkit

LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference

PyTorch Implementation of CvT: Introducing Convolutions to Vision Transformers

Sign Language Transformers (CVPR'20)

Official pytorch implementation of paper "Inception Convolution with Efficient Dilation Search" (CVPR 2021 Oral).

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

RepVGG: Making VGG-style ConvNets Great Again

This code repository presents the pytorch implementation of the paper “Structure-Aware Human-ActionGeneration”(ECCV 2020).

Graph Convolutional Networks in PyTorch

An out-of-box human parsing representation extractor.

A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.

Efficient 3D human pose estimation in video using 2D keypoint trajectories

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

This is an official pytorch implementation of “Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimates” (https://arxiv.org/abs/2006.15480).

【CVPR2020, Interpretable Network】A Model-driven Deep Neural Network for Single Image Rain Removal

tensorflow implementation for "High-Resolution Representations for Labeling Pixels and Regions"

This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)

Positional Normalization (PONO) and Moment Shortcut (MS)