|国家预印本平台
首页|Refine Any Object in Any Scene

Refine Any Object in Any Scene

Refine Any Object in Any Scene

来源:Arxiv_logoArxiv
英文摘要

Viewpoint missing of objects is common in scene reconstruction, as camera paths typically prioritize capturing the overall scene structure rather than individual objects. This makes it highly challenging to achieve high-fidelity object-level modeling while maintaining accurate scene-level representation. Addressing this issue is critical for advancing downstream tasks requiring detailed object understanding and appearance modeling. In this paper, we introduce Refine Any object In any ScenE (RAISE), a novel 3D enhancement framework that leverages 3D generative priors to recover fine-grained object geometry and appearance under missing views. Starting from substituting degraded objects with proxies, via a 3D generative model with strong 3D understanding, RAISE progressively refines geometry and texture by aligning each proxy to its degraded counterpart in 7-DOF pose, followed by correcting spatial and appearance inconsistencies via registration-constrained enhancement. This two-stage refinement ensures the high-fidelity geometry and appearance of the original object in unseen views while maintaining consistency in spatial positioning, observed geometry, and appearance. Extensive experiments on challenging benchmarks show that RAISE significantly outperforms state-of-the-art methods in both novel view synthesis and geometry completion tasks. RAISE is made publicly available at https://github.com/PolySummit/RAISE.

Ziwei Chen、Ziling Liu、Zitong Huang、Mingqi Gao、Feng Zheng

计算技术、计算机技术

Ziwei Chen,Ziling Liu,Zitong Huang,Mingqi Gao,Feng Zheng.Refine Any Object in Any Scene[EB/OL].(2025-06-30)[2025-07-25].https://arxiv.org/abs/2506.23835.点此复制

评论