Research map / 3D vision / 3D generation
AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation
Xinzhou Wang, Yikai Wang, Junliang Ye, Fuchun Sun, Zhengyi Wang, Ling Wang, Pengkun Liu, Kai Sun, Xintong Wang, Xie wende, Fangfu Liu, Bin He
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 skeleton loss L_skel (ablation) | AnimatableDreamer CSD · Text-to-4D generation | CLIP: 28.4 -> 38.2 | Improved |
| add bone loss L_bone (ablation) | AnimatableDreamer CSD · Text-to-4D generation | R-Precision@10: 81.7 -> 87.5 | Improved |
| add bone loss L_bone (ablation) | AnimatableDreamer CSD · Text-to-4D generation | CLIP: 37.8 -> 38.2 | No clear effect |
| add CSD loss to reconstruction (ablation) | AnimatableDreamer · Cat-Coco monocular reconstruction | Chamfer distance (cm): 8.34 -> 3.65 | Improved |
| add CSD loss to reconstruction (ablation) | AnimatableDreamer · Cat-Pikachu monocular reconstruction | F-score (%): 59.6 -> 88.9 | Improved |
| use diffusion prior with one video instead of four videos for BANMo | AnimatableDreamer vs BANMo · Cat-Coco | Chamfer distance (cm): 4.66 -> 3.65 | Improved |
| canonical score distillation versus MVDream and ProlificDreamer | text-to-4D generation · Casual Videos | GPT Eval3D elo: 979 -> 1098 | Improved |
Closest papers by meaning
- Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models (CVPR 2024 · similarity 0.86)
- 4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling (CVPR 2024 · similarity 0.86)
- SKDream: Controllable Multi-view and 3D Generation with Arbitrary Skeletons (CVPR 2025 · similarity 0.86)
- Animate3D: Animating Any 3D Model with Multi-view Video Diffusion (NeurIPS 2024 · similarity 0.86)
- Articulated Kinematics Distillation from Video Diffusion Models (CVPR 2025 · similarity 0.86)
- Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters (CVPR 2025 · 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.
