AI Paper Atlas

Research map / 3D vision / Depth and stereo

UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass

Mengfei Li, Peng Li, Zheng Zhang, Jiahao Lu, Chengfeng Zhao, Wei Xue, Qifeng Liu, Sida Peng, Wenxiao Zhang, Wenhan Luo, Yuan Liu, Yike Guo

CVPR 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 11 citations (OpenAlex)

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
Fine-tune π3 on synthetic BEDLAM with original objective (ablation)π3 · Bonn video depthAbs Rel: 0.049 -> 0.062Hurt
Mix BEDLAM with real data in refinement (ablation)π3 · Bonn video depthAbs Rel: 0.049 -> 0.051Hurt
Distill human-centric local loss from MoGe-2 pseudo-depth on unlabeled real data (ablation)π3 · Bonn video depthAbs Rel: 0.049 -> 0.035Improved
Add human-surface refinement (ablation)π3 · Bonn video depthdelta<1.25: 0.975 -> 0.980Improved
Supervise scene branch directly for metric scale (no AlignNet scale prediction) (ablation)UniSH · in-the-wild videosqualitativeHurt
Add fine-grained alignment on unlabeled real data after coarse synthetic alignment (ablation)UniSH · in-the-wild SMPL-scene alignmentqualitativeImproved
Use UniSH vs GVHMR on global motionUniSH · EMDB-2WA-MPJPE: 111.0 (GVHMR) vs 118.5 (UniSH)Hurt
Use UniSH vs JOSH3R (feed-forward joint)UniSH · EMDB-2WA-MPJPE: 220.0 -> 118.5Improved
Use UniSH vs GVHMR on RICHUniSH · RICHWA-MPJPE: 78.8 vs 118.1Hurt

Later papers that compared with this method

3 later accepted papers report UniSH as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 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