Stars
Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction
[NeurIPS 2023] Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"
Official code release for the project "3D-QAE: A Fully Quantum Auto-Encoder for 3D Shapes
SlackedFace
code of RMFER: Semi-supervised Contrastive Learning for Facial Expression Recognition with Reaction Mashup Video
Implementation of Robust Imitation Learning against Variations in Environment Dynamics
Official repository for SlaBins: Fisheye Depth Estimation using Slanted Bins on Road Environments (ICCV 2023)
Carousel Memory: Rethinking the Design of Episodic Memory for Continual Learning
Domain generalization method code based on DomainBed
[SenSys 2023] On-NAS: On-Device Neural Architecture Search on Memory-Constrained Intelligent Embedded Systems
Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations
NeurIPS 2023 - TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models Official Code
Can We Find Strong Lottery Tickets in Generative Models? - Official Code (Pytorch)
A repository of a paper named "Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?", accepted to ICRA 2023.
Code for "Contextual Instance Decoupling for Robust Multi-Person Pose Estimation", CVPR 2022 Oral
Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)
Official Pytorch implementation of "Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes", CVPR 2022
Code for ICCV2021 paper PARE: Part Attention Regressor for 3D Human Body Estimation
Official Pytorch implementation of "Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video", CVPR 2021
Edit files on ftp servers with Atom editor and without a workspace.
Solutions of Reinforcement Learning, An Introduction
This repository is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). Proposed method archives state-of-the-art results in multi-view 3D huma…