Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.23835 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914050178285568 |
|---|---|
| author | Chen, Ziwei Liu, Ziling Huang, Zitong Gao, Mingqi Zheng, Feng |
| author_facet | Chen, Ziwei Liu, Ziling Huang, Zitong Gao, Mingqi Zheng, Feng |
| contents | 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 high-fidelity object reconstruction. In this paper, we introduce Scene-Consistent Object Refinement via Proxy Generation and Tuning (SCORP), a novel 3D enhancement framework that leverages 3D generative priors to recover fine-grained object geometry and appearance under missing views. Starting with proxy generation by substituting degraded objects using a 3D generation model, SCORP then progressively refines geometry and texture by aligning each proxy to its degraded counterpart in 7-DoF pose, followed by correcting spatial and appearance inconsistencies through registration-constrained enhancement. This two-stage proxy tuning ensures the high-fidelity geometry and appearance of the original object in unseen views while maintaining consistency in spatial positioning, observed geometry, and appearance. Across challenging benchmarks, SCORP achieves consistent gains over recent state-of-the-art baselines on both novel view synthesis and geometry completion tasks. SCORP is available at https://github.com/PolySummit/SCORP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23835 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCORP: Scene-Consistent Object Refinement via Proxy Generation and Tuning Chen, Ziwei Liu, Ziling Huang, Zitong Gao, Mingqi Zheng, Feng Computer Vision and Pattern Recognition 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 high-fidelity object reconstruction. In this paper, we introduce Scene-Consistent Object Refinement via Proxy Generation and Tuning (SCORP), a novel 3D enhancement framework that leverages 3D generative priors to recover fine-grained object geometry and appearance under missing views. Starting with proxy generation by substituting degraded objects using a 3D generation model, SCORP then progressively refines geometry and texture by aligning each proxy to its degraded counterpart in 7-DoF pose, followed by correcting spatial and appearance inconsistencies through registration-constrained enhancement. This two-stage proxy tuning ensures the high-fidelity geometry and appearance of the original object in unseen views while maintaining consistency in spatial positioning, observed geometry, and appearance. Across challenging benchmarks, SCORP achieves consistent gains over recent state-of-the-art baselines on both novel view synthesis and geometry completion tasks. SCORP is available at https://github.com/PolySummit/SCORP. |
| title | SCORP: Scene-Consistent Object Refinement via Proxy Generation and Tuning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.23835 |