Research map / Video / Video generation
FineXtrol: Controllable Motion Generation via Fine-Grained Text
Keming Shen, Bizhu Wu, Junliang Chen, Xiaoqin Wang, Linlin Shen
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 |
|---|---|---|---|
| use residual dual-branch control guidance instead of concatenating control text with coarse text (ablation) | FineXtrol · HumanML3D test | FID: 1.383 -> 0.245 | Improved |
| use hierarchical-contrastive T5 instead of CLIP (ablation) | FineXtrol · HumanML3D test | FID: 0.579 -> 0.245 | Improved |
| use hierarchical-contrastive T5 instead of vanilla T5 (ablation) | FineXtrol · HumanML3D test | FID: 0.374 -> 0.245 | Improved |
| add fine-grained text control signals | MDM · HumanML3D test | FID: 0.544 -> 0.245 | Improved |
| multi-part control (Cross) vs single-part average | FineXtrol · HumanML3D test | FID: 0.245 -> 0.351 | Hurt |
| FineXtrol text control vs OmniControl coordinate control | FineXtrol · HumanML3D test (avg over body parts) | FID: 0.245 vs 0.255 (OmniControl); InterControl 0.209 | Mixed |
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.
- CoMo — CoMo: Controllable Motion Generation through Language Guided Pose Code Editing (ECCV 2024) · better on 4 of 4 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
- Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs (NeurIPS 2023 · similarity 0.91)
- Enhanced Fine-Grained Motion Diffusion for Text-Driven Human Motion Synthesis (AAAI 2024 · similarity 0.88)
- DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control (ICLR 2025 · similarity 0.88)
- OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers (CVPR 2024 · similarity 0.88)
- MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators (AAAI 2024 · similarity 0.87)
- MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities (CVPR 2025 · 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.
