AI Paper Atlas

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

CVPR 2026 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture

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 changedWhereMeasuredEffect
replace 4D reconstruction baselines (MonST3R, SpatialTrackerV2) with FunREC articulation-aware tracking and part segmentationmoving-part segmentation · OmniFun4DmIoU: 23.6 -> 77.9Improved
use FunREC joint part-pose and articulation optimization vs best baseline6D part pose · OmniFun4DADD-S (%): 37.12 -> 78.96Improved
give baselines ground-truth depthMonST3R / SpatialTrackerV2 · OmniFun4D 6D part poseADD-S (%): 33.58 -> 37.12 (MonST3R), 26.94 -> 29.71 (SpatialTrackerV2)Mixed
use FunREC instead of BundleSDF with GT masks for articulation axisarticulation estimation · OmniFun4Daxis direction error (deg, revolute): 38.2 -> 5.3Improved
use FunREC instead of BundleSDF on failure ratearticulation estimation · OmniFun4Dfailure rate (%): 55.0 -> 1.7Improved
FunREC vs best baseline reconstruction on HOI4Dreconstruction · HOI4DChamfer Distance (cm): 0.8 -> 0.7No clear effect
FunREC vs best baseline reconstruction on RealFun4Dreconstruction · RealFun4DChamfer Distance (cm): 10.6 -> 6.1Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy