Research map / Video / Video generation
X-MoGen: Unified Motion Generation Across Humans and Animals
Xuan Wang, Kai Ruan, Liyang Qian, Guo Zhi Zhi, Chang Su, Gaoang Wang
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 CLIP word-level text features (ablation) | X-MoGen · UniMo4D test | FID: 0.053 -> 0.050 | Improved |
| add CGAE T-pose prior (ablation) | X-MoGen · UniMo4D test | MME: 0.228 -> 0.201 | Improved |
| add AE morphological reconstruction loss (ablation) | X-MoGen · UniMo4D test | FID: 0.108 -> 0.050 | Improved |
| add morphological consistency module (ablation) | X-MoGen · UniMo4D test | MME: 0.238 -> 0.201 | Improved |
| add morphological consistency module (ablation) | X-MoGen · UniMo4D test | FID: 0.049 -> 0.050 | No clear effect |
| use continuous AE instead of VQ/FSQ/RVQ quantization (ablation) | X-MoGen · UniMo4D test | FID (reconstruction): 0.451 -> 0.008 (vs RVQ) | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- AniMo — AniMo: Species-Aware Model for Text-Driven Animal Motion Generation (CVPR 2025) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- OmniMotionGPT: Animal Motion Generation with Limited Data (CVPR 2024 · similarity 0.91)
- How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects (ICML 2025 · similarity 0.90)
- The Quest for Generalizable Motion Generation: Data, Model, and Evaluation (ICLR 2026 · similarity 0.89)
- SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology (NeurIPS 2026 · similarity 0.89)
- AniMo: Species-Aware Model for Text-Driven Animal Motion Generation (CVPR 2025 · similarity 0.88)
- MMM: Generative Masked Motion Model (CVPR 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.
