通过多视角同步修复3D重建中的语义与几何不一致问题。
SyncFix: Fixing 3D Reconstructions via Multi-View Synchronization
- 利用联合潜在空间匹配，跨视角同步修正畸变与干净表示。
- 在无参考图像时仍超越现有最佳方法，多视角提升重建质量。
- 适用于任意数量视角，稀疏参考下可进一步提高保真度。
我们提出SyncFix，一种在基于扩散模型的场景精细化过程中强制跨视角一致性的框架。SyncFix将精修过程建模为联合潜在桥接匹配问题，通过同步多个视角间的扭曲与干净表示，修复语义和几何不一致。这意味着SyncFix学习多视角联合条件，以在整个去噪轨迹中维持一致性。训练仅需图像对，但推理时能自然扩展至任意数量视角。重建质量随视角增多而提升，高视图数时收益递减。定性和定量结果表明，SyncFix始终生成高质量重建，即使在无清洁参考图像的情况下也优于当前最先进基线；当存在稀疏参考时，保真度进一步提升。
原文摘要 · Abstract (English)
We present SyncFix, a framework that enforces cross-view consistency during the diffusion-based refinement of reconstructed scenes. SyncFix formulates refinement as a joint latent bridge matching problem, synchronizing distorted and clean representations across multiple views to fix the semantic and geometric inconsistencies. This means SyncFix learns a joint conditional over multiple views to enforce consistency throughout the denoising trajectory. Our training is done only on image pairs, but it generalizes naturally to an arbitrary number of views during inference. Moreover, reconstruction quality improves with additional views, with diminishing returns at higher view counts. Qualitative and quantitative results demonstrate that SyncFix consistently generates high-quality reconstructions and surpasses current state-of-the-art baselines, even in the absence of clean reference images. SyncFix achieves even higher fidelity when sparse references are available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。