Research map / 3D vision / 3D generation
4D Primitive-Mache: Glueing Primitives for Persistent 4D Scene Reconstruction
Kirill Mazur, Marwan Taher, Andrew J. Davison
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 |
|---|---|---|---|
| glue primitives across time with rigid per-primitive SE(3) poses on top of pi3 outputs | pi3 (untouched feed-forward estimate) · HO3D (dynamic parts) | avg F-score: 0.5219 -> 0.7573 | Improved |
| glue primitives across time with rigid per-primitive SE(3) poses on top of pi3 outputs | pi3 (untouched feed-forward estimate) · Multi-Object dataset | mean F-score: 0.4799 -> 0.7948 | Improved |
| aggregate observations from all keyframes instead of using only the last frame pointmap | pi3 last view · HO3D (dynamic parts) | recall: 0.2018 -> 0.7774 | Improved |
| use only last-frame pointmap versus the 4DPM aggregation | pi3 last view · HO3D (dynamic parts) | precision: 0.9255 -> 0.7630 | Hurt |
| 4DPM versus pi3 last view on precision in Multi-Object dataset | 4DPM · Multi-Object dataset | precision: 0.8837 -> 0.7195 | Hurt |
| use primitive motion grouping through contact and velocity similarity to keep occluded objects | 4DPM · closing drawer sequence | qualitative object permanence | 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.
- POMATO — POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction (ICCV 2025) · better on 2 of 2 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
- FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction (CVPR 2025 · similarity 0.88)
- Instant4D: 4D Gaussian Splatting in Minutes (NeurIPS 2025 · similarity 0.88)
- 4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time (NeurIPS 2025 · similarity 0.88)
- Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video (ICLR 2024 · similarity 0.88)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.88)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (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.
