Research map / 3D vision / 3D generation
Choreographing a World of Dynamic Objects
Yanzhe Lyu, Chen Geng, Karthik Dharmarajan, Yunzhi Zhang, Hadi Alzayer, Shangzhe Wu, Jiajun Wu
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 annealed weighted noise-level sampling (instead of uniform sampling with weighting) (ablation) | CHORD · Multi-object 4D scene animation | motion realism (qualitative) | Improved |
| add Fenwick tree temporal representation (ablation) | CHORD · Multi-object 4D scene animation | artifacts in later frames (qualitative) | Improved |
| add fine control-point layer (ablation) | CHORD · Multi-object 4D scene animation | motion detail (qualitative) | Improved |
| add coarse control points (ablation) | CHORD · Multi-object 4D scene animation | distortion (qualitative) | Improved |
| start with coarse level then add fine level (vs fine layer from the beginning) (ablation) | CHORD · Multi-object 4D scene animation | artifacts (qualitative) | Improved |
| add temporal regularization (ablation) | CHORD · Multi-object 4D scene animation | temporal flicker (qualitative) | Improved |
| add spatial ARAP regularization (ablation) | CHORD · Multi-object 4D scene animation | visual artifacts (qualitative) | 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.
- Animate3D — Animate3D: Animating Any 3D Model with Multi-view Video Diffusion (NeurIPS 2024) · 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
- Advances in 4D Generation: Techniques, Challenges, and Future Directions (TPAMI 2026 · similarity 0.90)
- Geometry-aware 4D Video Generation for Robot Manipulation (ICLR 2026 · similarity 0.90)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.88)
- DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos (NeurIPS 2024 · similarity 0.88)
- 4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models (NeurIPS 2024 · similarity 0.88)
- DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation (NeurIPS 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.
