UniFixer: A Universal Reference-Guided Fixer for Diffusion-Based View Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Sihan, Zhang, Xiang, Zhang, Yang, Aydin, Tunc, Schroers, Christopher
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911675284717568
author Chen, Sihan
Zhang, Xiang
Zhang, Yang
Aydin, Tunc
Schroers, Christopher
author_facet Chen, Sihan
Zhang, Xiang
Zhang, Yang
Aydin, Tunc
Schroers, Christopher
contents With the recent surge of generative models, diffusion-based approaches have become mainstream for view synthesis tasks, either in an explicit depth-warp-inpaint or in an implicit end-to-end manner. Despite their success, both paradigms often suffer from noticeable quality degradation, e.g., blurred details and distorted structures, caused by pixel-to-latent compression and diffusion hallucination. In this paper, we investigate diffusion degradation from three key dimensions (i.e., spatial, temporal, and backbone-related) and propose UniFixer, a universal reference-guided framework that fixes diverse degradation artifacts via a coarse-to-fine strategy. Specifically, a reference pre-alignment module is first designed to perform coarse alignment between the reference view and the degraded novel view. A global structure anchoring mechanism then rectifies geometric distortions to ensure structural fidelity, followed by a local detail injection module that recovers fine-grained texture details for high-quality view synthesis. Our UniFixer serves as a plug-and-play refiner that achieves zero-shot fixing across different types of diffusion degradation, and extensive experiments verify our state-of-the-art performance on novel view synthesis and stereo conversion.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12169
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UniFixer: A Universal Reference-Guided Fixer for Diffusion-Based View Synthesis
Chen, Sihan
Zhang, Xiang
Zhang, Yang
Aydin, Tunc
Schroers, Christopher
Computer Vision and Pattern Recognition
With the recent surge of generative models, diffusion-based approaches have become mainstream for view synthesis tasks, either in an explicit depth-warp-inpaint or in an implicit end-to-end manner. Despite their success, both paradigms often suffer from noticeable quality degradation, e.g., blurred details and distorted structures, caused by pixel-to-latent compression and diffusion hallucination. In this paper, we investigate diffusion degradation from three key dimensions (i.e., spatial, temporal, and backbone-related) and propose UniFixer, a universal reference-guided framework that fixes diverse degradation artifacts via a coarse-to-fine strategy. Specifically, a reference pre-alignment module is first designed to perform coarse alignment between the reference view and the degraded novel view. A global structure anchoring mechanism then rectifies geometric distortions to ensure structural fidelity, followed by a local detail injection module that recovers fine-grained texture details for high-quality view synthesis. Our UniFixer serves as a plug-and-play refiner that achieves zero-shot fixing across different types of diffusion degradation, and extensive experiments verify our state-of-the-art performance on novel view synthesis and stereo conversion.
title UniFixer: A Universal Reference-Guided Fixer for Diffusion-Based View Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.12169