AI Paper Atlas

Research map / 3D vision / Human pose estimation

UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair

Chuanrui Zhang, Yingshuang Zou, ZhengXian Wu, Yonggen Ling, Yuxiao Yang, Ziwei Wang

CVPR 2026 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 0 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
add Pose-Aware Shape Representation (PASR) in place of canonical shape reconstruction (ablation)UniPR · LVS6D Hard subsetACD: 12.363 -> 1.224Improved
add PASR to the Coders baseline (ablation)Coders · LVS6D Hard subsetACD: 10.146 -> 1.816Improved
use stereo input instead of left image only (ablation)UniPR · LVS6D Hard subsetAP: 0.270 -> 0.752Improved
use spherical voxel space instead of cubic (ablation)UniPR · LVS6D Hard subsetAP / ACD: AP 0.677 -> 0.752; ACD 1.310 -> 1.224; APE 1.129 -> 1.248Mixed
end-to-end whole-scene single pass versus per-object image-to-3D pipelinesUniPR · 5-object sceneInference time (s): 370.78 -> 0.63Improved
use UniPR instead of Trellis/Hunyuan2.1 given GT masks and posesshape reconstruction · LVS6D reconstruction (50 objects)Shape Proportion Error: 0.320 -> 0.109Improved
UniPR with pose decoding layer versus Coders on TODUniPR · TOD3D50: 99.8 -> 97.5Hurt

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