XBuzhe
Follow
Stars
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
Code for our CVPR'23 paper - "PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Lattices"
[CVPR2024(Highlight)] NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors
[T-PAMI 2022] Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
ECCV2020 - Official code repository for the paper : STAR - A Sparse Trained Articulated Human Body Regressor
[CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution
[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research
Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021
PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimation
Codes for the CVPR 2024 paper: "KITRO: Refining Human Mesh by 2D Clues and Kinematic-tree Rotation"
An Blender addon uses ROMP to extract human's 3D poses from image, video or webcam and drive your own 3D character.
Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]
Repository for ICCV23 paper: "ReFit: Recurrent Fitting Network for 3D Human Recovery"
visualization code for 3D human body annotation by EFT (Exemplar Fine-tuning)
3D Pseudo-GTs of "NeuralAnnot: Neural Annotator for 3D Human Mesh Training Sets", CVPRW 2022 Oral.
ScoreHMR: Score-Guided Diffusion for 3D Human Recovery (CVPR 2024)
The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"
OpenMMLab Pose Estimation Toolbox and Benchmark.
[CVPR 2023] Official implementation of the paper "One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer"
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.