Saved in:
Bibliographic Details
Main Authors: Zhang, Chuanrui, Zou, Yingshuang, Wu, ZhengXian, Ling, Yonggen, Yang, Yuxiao, Wang, Ziwei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.19616
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914410225729536
author Zhang, Chuanrui
Zou, Yingshuang
Wu, ZhengXian
Ling, Yonggen
Yang, Yuxiao
Wang, Ziwei
author_facet Zhang, Chuanrui
Zou, Yingshuang
Wu, ZhengXian
Ling, Yonggen
Yang, Yuxiao
Wang, Ziwei
contents Perceiving and reconstructing objects from images are critical for real-to-sim transfer tasks, which are widely used in the robotics community. Existing methods rely on multiple submodules such as detection, segmentation, shape reconstruction, and pose estimation to complete the pipeline. However, such modular pipelines suffer from inefficiency and cumulative error, as each stage operates on only partial or locally refined information while discarding global context. To address these limitations, we propose UniPR, the first end-to-end object-level real-to-sim perception and reconstruction framework. Operating directly on a single stereo image pair, UniPR leverages geometric constraints to resolve the scale ambiguity. We introduce Pose-Aware Shape Representation to eliminate the need for per-category canonical definitions and to bridge the gap between reconstruction and pose estimation tasks. Furthermore, we construct a large-vocabulary stereo dataset, LVS6D, comprising over 6,300 objects, to facilitate large-scale research in this area. Extensive experiments demonstrate that UniPR reconstructs all objects in a scene in parallel within a single forward pass, achieving significant efficiency gains and preserves true physical proportions across diverse object types, highlighting its potential for practical robotic applications.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19616
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair
Zhang, Chuanrui
Zou, Yingshuang
Wu, ZhengXian
Ling, Yonggen
Yang, Yuxiao
Wang, Ziwei
Computer Vision and Pattern Recognition
Perceiving and reconstructing objects from images are critical for real-to-sim transfer tasks, which are widely used in the robotics community. Existing methods rely on multiple submodules such as detection, segmentation, shape reconstruction, and pose estimation to complete the pipeline. However, such modular pipelines suffer from inefficiency and cumulative error, as each stage operates on only partial or locally refined information while discarding global context. To address these limitations, we propose UniPR, the first end-to-end object-level real-to-sim perception and reconstruction framework. Operating directly on a single stereo image pair, UniPR leverages geometric constraints to resolve the scale ambiguity. We introduce Pose-Aware Shape Representation to eliminate the need for per-category canonical definitions and to bridge the gap between reconstruction and pose estimation tasks. Furthermore, we construct a large-vocabulary stereo dataset, LVS6D, comprising over 6,300 objects, to facilitate large-scale research in this area. Extensive experiments demonstrate that UniPR reconstructs all objects in a scene in parallel within a single forward pass, achieving significant efficiency gains and preserves true physical proportions across diverse object types, highlighting its potential for practical robotic applications.
title UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.19616