PR-IQA: Partial-Reference Image Quality Assessment for Diffusion-Based Novel View Synthesis
This work addresses a specific problem in 3D reconstruction and novel view synthesis for computer vision applications, offering an incremental improvement by enhancing existing diffusion-augmented pipelines.
The paper tackles the problem of photometric and geometric inconsistencies in diffusion-generated views for novel view synthesis by proposing PR-IQA, a framework that evaluates these views using reference images from different poses without ground truth, and integrates it into a 3DGS pipeline to restrict supervision to high-confidence regions, resulting in superior 3D reconstructions and NVS results.
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/.