arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.04576cs.CV
收藏

PR-IQA:基于扩散模型的新型视角合成的部分参考图像质量评估

PR-IQA: Partial-Reference Image Quality Assessment for Diffusion-Based Novel View Synthesis

Dongguk University(东国大学);NAVER WEBTOON AI

Inseong Choi, Siwoo Lee, Seung-Hun Nam, Soohwan Song

AI总结:

PR-IQA通过部分参考图像评估扩散生成的视角合成图像质量,提升3D重建效果,无需真实地面真值。

摘要:

扩散模型在稀疏视角新型视角合成(NVS)中具有潜力,因为它们可以生成伪地面真实视角以帮助3D重建管道,如3D高斯点划法(3DGS)。然而,这些合成图像经常包含光度和几何不一致,直接用于监督会损害重建。为此,我们提出了部分参考图像质量评估(PR-IQA),一种框架,通过不同姿态的参考图像评估扩散生成的视角,消除对真实地面真值的需求。PR-IQA首先在重叠区域计算几何一致的部分质量图。然后进行质量完成,将此部分图填充为密集的全图像图。此完成通过交叉注意机制实现,结合参考视角上下文,确保跨视角一致性,并实现彻底的质量评估。当整合到扩散增强的3DGS管道中时,PR-IQA将监督限制在由其质量图识别的高置信度区域。实验表明,PR-IQA优于现有IQA方法,达到全参考级别的准确性而无需真实地面真值监督。因此,我们的质量感知3DGS方法更有效地过滤不一致,产生更优的3D重建和NVS结果。项目页面可在https://kakaomacao.github.io/pr-iqa-project-page/上找到。

英文摘要:

Diffusion models are promising for sparse-view novel view synthesis (NVS), as they can generate pseudo-ground-truth views to aid 3D reconstruction pipelines like 3D Gaussian Splatting (3DGS). However, these synthesized images often contain photometric and geometric inconsistencies, and their direct use for supervision can impair reconstruction. To address this, we propose Partial-Reference Image Quality Assessment (PR-IQA), a framework that evaluates diffusion-generated views using reference images from different poses, eliminating the need for ground truth. PR-IQA first computes a geometrically consistent partial quality map in overlapping regions. It then performs quality completion to inpaint this partial map into a dense, full-image map. This completion is achieved via a cross-attention mechanism that incorporates reference-view context, ensuring cross-view consistency and enabling thorough quality assessment. When integrated into a diffusion-augmented 3DGS pipeline, PR-IQA restricts supervision to high-confidence regions identified by its quality maps. Experiments demonstrate that PR-IQA outperforms existing IQA methods, achieving full-reference-level accuracy without ground-truth supervision. Thus, our quality-aware 3DGS approach more effectively filters inconsistencies, producing superior 3D reconstructions and NVS results. The project page is available at https://kakaomacao.github.io/pr-iqa-project-page/.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑