Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

Refine high-quality datasets and visual AI models

This is the official code release for our work, Denoising Vision Transformers.

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

Official Code for DragGAN (SIGGRAPH 2023)

[CVPR 2023] Executing your Commands via Motion Diffusion in Latent Space, a fast and high-quality motion diffusion model

[CVPR 2023] Official implementation of the paper "One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer"

Code of "NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation", CVPR 2023

本人的科研经验

A NS-3 implementation of Poseidon congestion control algorithm (NSDI 2023).

[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration

Download resources from online storage with ONLY ONE command line!!

[CVPR 2022 Oral] Official PyTorch Implementation of "GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras”.

The code accompanying our ECCV'22 papers: Constructing Balance from Imbalance for Long-tailed Image Recognition

[ECCV 2022] Official implementation of the paper "SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos"

Official code for ECCV paper "Unsupervised Visual Representation Learning by Synchronous Momentum Grouping"

Code for "D&D: Learning Human Dynamics from Dynamic Camera", ECCV 2022 Oral

Official repository for CVPR 2022 paper: I M Avatar: Implicit Morphable Head Avatars from Videos

Official PyTorch implementation of the paper "TEMOS: Generating diverse human motions from textual descriptions", ECCV 2022 (Oral)

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

[ECCV 2022] Official implementation of the paper "DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation"

Chrome/Safari/Firefox extension for clipping arXiv articles to Notion.

Code for "Localization with Sampling-Argmax", NeurIPS 2021

Unpaired line drawing generation

A real-time system that captures physically correct human motion, joint torques, and ground reaction forces with only 6 inertial measurement units

[CVPR 2022 Oral] ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis