CVI-SZU / MG-MotionLLMLinks
[CVPR 2025] MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities
☆26Updated 2 months ago
Alternatives and similar repositories for MG-MotionLLM
Users that are interested in MG-MotionLLM are comparing it to the libraries listed below
Sorting:
- FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing☆15Updated 3 months ago
- Official implementation of "FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis"☆42Updated 8 months ago
- OpenTMA: support text-motion alignment for HumanML3D, Motion-X, and UniMoCap☆38Updated last year
- ☆17Updated 3 months ago
- ☆22Updated last year
- MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations☆35Updated 8 months ago
- Official implement of "AMD: Autoregressive Motion Diffusion"☆19Updated 7 months ago
- The official implementation of work "AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward".☆15Updated 3 months ago
- ☆30Updated 2 months ago
- ☆47Updated last year
- Official implementation for "Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches" (CVPR 2024)☆23Updated 11 months ago
- InterFormer method to generate a reaction motion based on an action motion with 3D skeletons☆25Updated 2 years ago
- ECCV 2024: Controllable Motion Generation through Language Guided Pose Code Editing☆45Updated 6 months ago
- ☆12Updated 3 weeks ago
- Repo for "Human-Centric Foundation Models: Perception, Generation and Agentic Modeling" (https://arxiv.org/abs/2502.08556)☆49Updated 4 months ago
- FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing☆17Updated 2 months ago
- Code for ReMoS: 3D-Motion Conditioned Reaction Synthesis for Two-person Interactions (ECCV 2024)☆20Updated 3 months ago
- ☆9Updated last year
- Towards Variable and Coordinated Holistic Co-Speech Motion Generation, CVPR 2024☆57Updated last year
- M3GPT: An advanced multimodal, multitask framework for motion comprehension and generation.☆15Updated 6 months ago
- [CVPR 2024] Official implementation of the paper "ReGenNet: Towards Human Action-Reaction Synthesis"☆54Updated 9 months ago
- ☆22Updated last year
- [CVPR 2025] UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing☆27Updated 2 months ago
- ☆74Updated 3 weeks ago
- Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation (AAAI 2025)☆26Updated 3 months ago
- ☆10Updated 8 months ago
- The official PyTorch implementation of "The 18th European Conference on Computer Vision" (ECCV 2024) paper Length-Aware Motion Synthesis …☆20Updated 6 months ago
- Official code release of "DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding"☆30Updated this week
- ☆39Updated 5 months ago
- Official pytorch implementation of MotionLLaMA based on MMEngine☆62Updated 4 months ago