Research map / Video / Video generation
T2Bs: Text-to-Character Blendshapes via Video Generation
Jiahao Luo, Chaoyang Wang, Michael Vasilkovsky, Vladislav Shakhrai, Di Liu, Peiye Zhuang, Sergey Tulyakov, Peter Wonka, Hsin-Ying Lee, James Davis, Jian 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 view-conditioned deformation to VCDGS (ablation) | VCDGS · Objaverse-XL geometry | point-to-point error: 0.0632 -> 0.0576 | Improved |
| add color offset prediction (RefineMLP) (ablation) | VCDGS · Objaverse-XL geometry | normal consistency error: 0.1851 -> 0.1611 | Improved |
| add linear blend skinning with control points instead of per-Gaussian deformation (ablation) | VCDGS · Objaverse-XL geometry | normal consistency error: 0.2654 -> 0.1611 | Improved |
| add RefineMLP under simulated temporal appearance inconsistency (ablation) | VCDGS · Objaverse-XL noisy textures | normal consistency error: 0.2430 -> 0.1671 | Improved |
| fit VCDGS on SV4D multi-view videos instead of 4Real-Video (ablation) | VCDGS · Objaverse-XL image quality | FID: 59.6 -> 56.6 | No clear effect |
| apply VCDGS to refine raw 4Real-Video output (ablation) | 4Real-Video · Objaverse-XL image quality | FID: 151.7 -> 59.6 | Improved |
| use 2000 control points instead of 200, 500 or 1000 (ablation) | VCDGS · qualitative facial motion | fine-grained motion capture | Improved |
| use skeletons from UniRig or MagicArticulate instead of KNN control points (ablation) | VCDGS · facial expressions | suitability | Hurt |
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.
- SV4D — SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency (ICLR 2025) · better on 3 of 3 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
- Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models (CVPR 2024 · similarity 0.88)
- Text-Guided 3D Face Synthesis - From Generation to Editing (CVPR 2024 · similarity 0.87)
- LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example (CVPR 2024 · similarity 0.87)
- Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation (CVPR 2024 · similarity 0.87)
- TapMo: Shape-aware Motion Generation of Skeleton-free Characters (ICLR 2024 · similarity 0.86)
- ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models (CVPR 2024 · similarity 0.86)
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.
