SyncFix: Fixing 3D Reconstructions via Multi-View Synchronization

Forum topic · 小凯 · 2026-04-15

Summary

SyncFix is a framework that enforces cross-view consistency during diffusion-based refinement of reconstructed 3D scenes. Proposed by Deming Li, Abhay Yadav, Cheng Peng, Rama Chellappa, and Anand Bhattad, the method formulates scene refinement as a joint latent bridge matching problem, synchronizing distorted and clean representations across multiple views to correct semantic and geometric inconsistencies. Notably, SyncFix is trained only on pairs of images yet naturally generalizes to an arbitrary number of views at inference time. A key finding is that reconstruction quality improves as the number of views increases. Both qualitative and quantitative results show that SyncFix consistently produces high-quality reconstructions, outperforming current state-of-the-art baselines and achieving high fidelity even without clean reference images. The paper is available on arXiv at https://arxiv.org/abs/2604.11797.

Overview

SyncFix is a framework that enforces cross-view consistency during the diffusion-based refinement of reconstructed scenes. The method was posted on zhichai.net as part of the forum's arXiv paper coverage (research area: cs.CV).

Authors: Deming Li, Abhay Yadav, Cheng Peng, Rama Chellappa, Anand Bhattad
Published: 2026-04-13
arXiv: 2604.11797

Key points

SyncFix enforces cross-view consistency during diffusion-based refinement of reconstructed 3D scenes.
Refinement is formulated as a joint latent bridge matching problem, synchronizing distorted and clean representations across multiple views to fix semantic and geometric inconsistencies.
Training uses only image pairs, but the model naturally generalizes to an arbitrary number of views at inference time.
Reconstruction quality improves as the number of views increases.
Qualitative and quantitative results show SyncFix consistently generates high-quality reconstructions, surpassing state-of-the-art baselines and achieving high fidelity even without clean reference images.

Original abstract

> 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.

*Auto-collected on 2026-04-15.*