Research map / Video / Video generation
MOGO: Residual Quantized Hierarchical Causal Transformer for Real-Time and Infinite-Length 3D Human Motion Generation
Dongjie Fu, Tengjiao Sun, Pengcheng Fang, Xiaohao Cai, Hansung Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Textual Condition Alignment (LLM CoT prompt decomposition) | MOGO · HumanML3D | FID: 0.064 -> 0.038 | Improved |
| add Textual Condition Alignment | MOGO · CMP (zero-shot) | FID: 10.388 -> 6.873 | Improved |
| add Textual Condition Alignment | MOGO · KIT-ML | FID: 0.313 -> 0.191 | Improved |
| increase quantization layers from 1 to 3 (ablation) | MoSA-VQ · VAE reconstruction | FID: 0.070 -> 0.021 | Improved |
| increase quantization layers from 6 to 7 (ablation) | MoSA-VQ · VAE reconstruction | FID: 0.016 -> 0.016 | No clear effect |
| use hierarchical deeper layers and narrower heads vs uniform (ablation) | RQHC-Transformer · HumanML3D | FID: 0.101 -> 0.038 | Improved |
| compare MOGO with TCA vs MotionAnything on HumanML3D FID | MOGO with TCA · HumanML3D | FID: 0.028 vs 0.038 | Hurt |
Closest papers by meaning
- Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression (CVPR 2025 · similarity 0.90)
- MoMask: Generative Masked Modeling of 3D Human Motions (CVPR 2024 · similarity 0.90)
- MMM: Generative Masked Motion Model (CVPR 2024 · similarity 0.89)
- Seamless Human Motion Composition with Blended Positional Encodings (CVPR 2024 · similarity 0.88)
- MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling (NeurIPS 2024 · similarity 0.88)
- AMD: Autoregressive Motion Diffusion (AAAI 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
