SIR-DIFF: Sparse Image Sets Restoration with Multi-View Diffusion Model
This addresses the ill-posed problem of restoring true scene information from degraded photographs for computer vision applications like 3D reconstruction.
The paper tackles image restoration by jointly denoising multiple photographs of the same scene, hypothesizing that degraded images contain complementary information. The multi-view diffusion model outperforms single-view and video-based methods on deblurring and super-resolution tasks, producing 3D consistent images.
The computer vision community has developed numerous techniques for digitally restoring true scene information from single-view degraded photographs, an important yet extremely ill-posed task. In this work, we tackle image restoration from a different perspective by jointly denoising multiple photographs of the same scene. Our core hypothesis is that degraded images capturing a shared scene contain complementary information that, when combined, better constrains the restoration problem. To this end, we implement a powerful multi-view diffusion model that jointly generates uncorrupted views by extracting rich information from multi-view relationships. Our experiments show that our multi-view approach outperforms existing single-view image and even video-based methods on image deblurring and super-resolution tasks. Critically, our model is trained to output 3D consistent images, making it a promising tool for applications requiring robust multi-view integration, such as 3D reconstruction or pose estimation.