Research map / 3D vision / Human pose estimation
FUN REC * Reconstructing Functional 3D Scenes from Egocentric Interaction Videos
Alexandros Delitzas, Chenyangguang Zhang, Alexey Gavryushin, Tommaso Di Mario, Boyang Sun, Rishabh Dabral, Leonidas Guibas, Christian Theobalt, Marc Pollefeys, Francis Engelmann, Daniel Barath
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 |
|---|---|---|---|
| replace 4D reconstruction baselines (MonST3R, SpatialTrackerV2) with FunREC articulation-aware tracking and part segmentation | moving-part segmentation · OmniFun4D | mIoU: 23.6 -> 77.9 | Improved |
| use FunREC joint part-pose and articulation optimization vs best baseline | 6D part pose · OmniFun4D | ADD-S (%): 37.12 -> 78.96 | Improved |
| give baselines ground-truth depth | MonST3R / SpatialTrackerV2 · OmniFun4D 6D part pose | ADD-S (%): 33.58 -> 37.12 (MonST3R), 26.94 -> 29.71 (SpatialTrackerV2) | Mixed |
| use FunREC instead of BundleSDF with GT masks for articulation axis | articulation estimation · OmniFun4D | axis direction error (deg, revolute): 38.2 -> 5.3 | Improved |
| use FunREC instead of BundleSDF on failure rate | articulation estimation · OmniFun4D | failure rate (%): 55.0 -> 1.7 | Improved |
| FunREC vs best baseline reconstruction on HOI4D | reconstruction · HOI4D | Chamfer Distance (cm): 0.8 -> 0.7 | No clear effect |
| FunREC vs best baseline reconstruction on RealFun4D | reconstruction · RealFun4D | Chamfer Distance (cm): 10.6 -> 6.1 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MonST3R — MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion (ICLR 2025) · better on 3 of 3 shared results
- SpatialTrackerV2 — SpatialTracker: Tracking Any 2D Pixels in 3D Space (CVPR 2024) · better on 1 of 1 shared result
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
- Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos (NeurIPS 2026 · similarity 0.86)
- Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting (ICLR 2025 · similarity 0.86)
- MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR 2024 · similarity 0.86)
- Hand-held Object Reconstruction from RGB Video with Dynamic Interaction (CVPR 2025 · similarity 0.86)
- UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.86)
- Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation (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.
