zgspose / DSTA
This is the code of our paper "Video-Based Human Pose Regression via Decoupled Space-Time Aggregation".
☆119Updated last month
Related projects: ⓘ
- [CVPR 2024] Official Code for "AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation☆189Updated last month
- [Arxiv-2024] MotionLLM: Understanding Human Behaviors from Human Motions and Videos☆214Updated 2 weeks ago
- The official PyTorch code for RoHM: Robust Human Motion Reconstruction via Diffusion.☆303Updated 2 months ago
- MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR2024 Oral)☆197Updated 3 months ago
- [CVPR 2024] TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation☆201Updated last week
- SATO: Stable Text-to-Motion Framework☆97Updated last month
- Official PyTorch implementation of "6DoF Head Pose Estimation through Explicit Bidirectional Interaction with Face Geometry," ECCV 2024☆59Updated 2 months ago
- ☆92Updated last month
- ☆204Updated 3 months ago
- Official repo for VGGHeads: A Large-Scale Synthetic Dataset for 3D Human Heads.☆130Updated 3 weeks ago
- ScoreHMR: Score-Guided Diffusion for 3D Human Recovery (CVPR 2024)☆379Updated 3 months ago
- [ECCV 2024] Official implementation of the paper "TAPTR: Tracking Any Point with Transformers as Detection"☆187Updated last month
- Code repository for the paper "On the Benefits of 3D Pose and Tracking for Human Action Recognition", (CVPR 2023)☆245Updated 8 months ago
- [CVPR 2024] Official Implementation of "Seamless Human Motion Composition with Blended Positional Encodings".☆199Updated 4 months ago
- Large Motion Model for Unified Multi-Modal Motion Generation☆163Updated 5 months ago
- ☆117Updated 2 months ago
- [NeurIPS 2023] Official implementation of the paper "Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset"☆530Updated 3 weeks ago
- Minimal code and examnples for inferencing Sapiens foundation human models in Pytorch☆61Updated 2 weeks ago
- [NeurIPS 2023] FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing☆102Updated 9 months ago
- The Data and Code of Prompt2Sign: The First Comprehensive Multilingual Sign Language Dataset.☆127Updated 2 months ago
- Pytorch demo code and models for Multi-HMR☆183Updated this week
- Code repository for the paper "Tracking People by Predicting 3D Appearance, Location & Pose". (CVPR 2022 Oral)☆277Updated 5 months ago
- ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model☆314Updated 5 months ago
- Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.☆80Updated last month
- Source code of the paper Scene-Aware 3D Multi-Human Motion Capture, EUROGRAPHICS 2023☆118Updated last year
- [ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces☆235Updated 8 months ago
- Official pytorch implementation of Action-GPT☆114Updated last year
- ☆56Updated 2 months ago
- Our model BUDDI learns the joint distribution of interacting people☆134Updated 2 months ago
- Code for ICLR 2024 paper "Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment"☆87Updated 5 months ago