luomingshuang / M3GPT
M3GPT: An advanced multimodal, multitask framework for motion comprehension and generation.
☆13Updated 4 months ago
Alternatives and similar repositories for M3GPT:
Users that are interested in M3GPT are comparing it to the libraries listed below
- ☆21Updated last year
- Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation (AAAI 2025)☆18Updated last month
- Official Implementation of AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis with the extension (…☆18Updated last year
- The official PyTorch implementation of "The 18th European Conference on Computer Vision" (ECCV 2024) paper Length-Aware Motion Synthesis …☆20Updated 4 months ago
- Code for ReMoS: 3D-Motion Conditioned Reaction Synthesis for Two-person Interactions (ECCV 2024)☆20Updated last month
- OpenTMA: support text-motion alignment for HumanML3D, Motion-X, and UniMoCap☆36Updated 11 months ago
- Optimal-State Dynamics Estimation for Physics-based Human Motion Capture from Videos☆13Updated 2 months ago
- Awesome-Text2Motion-Generation☆18Updated last year
- [CVPR 2025] Official implementation of the paper "SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction"☆20Updated last month
- Humos paper repository☆17Updated last month
- MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations☆33Updated 6 months ago
- Controllable Group Choreography using Contrastive Diffusion☆16Updated 8 months ago
- Official code release of "DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding"☆28Updated 3 months ago
- A list of awesome human motion generation papers. Continuing to be updated!!!☆32Updated 8 months ago
- KMM: Key Frame Mask Mamba for Extended Motion Generation☆14Updated 3 weeks ago
- Towards Variable and Coordinated Holistic Co-Speech Motion Generation, CVPR 2024☆53Updated 10 months ago
- Pytorch implementation of paper "DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion"☆24Updated last year
- Official implementation of ICCV 2023 Oral Paper "Role-Aware Interaction Generation from Textual Description"☆31Updated last year
- ☆52Updated 2 months ago
- The official implementation of work "AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward".☆15Updated last month
- Code for paper "RapVerse: Coherent Vocals and Whole-Body Motions Generations from Text"