Research map / 3D vision / 3D generation
Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis
Hongyuan Chen, Xingyu Chen, Zexiang Xu, Anpei Chen
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 |
|---|---|---|---|
| reconstruct motion on a reference mesh instead of per-frame generation and alignment (V2M4) | Motion 3-to-4 · Motion-80 short | Chamfer Distance: 0.3437 -> 0.1113 | Improved |
| reconstruct motion on a reference mesh instead of feed-forward Gaussian prediction (L4GM) | Motion 3-to-4 · Motion-80 short | Chamfer Distance: 0.3561 -> 0.1113 | Improved |
| use ground-truth static mesh as reference | Motion 3-to-4 · Motion-80 short | Chamfer Distance: 0.1113 -> 0.0437 | Improved |
| use ground-truth static mesh as reference | Motion 3-to-4 · Motion-80 short | FVD: 1175.89 -> 497.43 | Improved |
| frame-wise transformer on long sequences | Motion 3-to-4 · Motion-80 long | F-Score: 0.1652 (V2M4) -> 0.2347 | Improved |
| compare with L4GM on appearance | Motion 3-to-4 · Motion-80 short | FVD: 1120.67 (L4GM) vs 1175.89 | Hurt |
| compare with L4GM on appearance | Motion 3-to-4 · Motion-80 short | LPIPS: 0.1487 (L4GM) vs 0.1495 | Mixed |
| compare with baselines on Consistent4D | Motion 3-to-4 · Consistent4D | CLIP: 0.8482 (V2M4) -> 0.8609 | Improved |
| compare with baselines on Consistent4D | Motion 3-to-4 · Consistent4D | FVD: 1207.79 (L4GM) vs 1260.06 | 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.
- L4GM — L4GM: Large 4D Gaussian Reconstruction Model (NeurIPS 2024) · better on 8 of 8 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
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.90)
- Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models (NeurIPS 2024 · similarity 0.90)
- CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models (CVPR 2025 · similarity 0.89)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.89)
- Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos (CVPR 2025 · similarity 0.89)
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.89)
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.
