A unified Benchmark for Multi-Frame Image Restoration under Severe Refractive Warping
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909018047381504 |
|---|---|
| author | Shugaev, Maxim V. Hoque, Md Reshad Ul Kennedy, Bridget Riley, Joseph T. Hwang, Fiona Hagen, Justin Ghuman, Harvir Garcia-O'Donnell, Ethan Qadri, Syed Noor Santiago, Freddie Lee, Mun Wai |
| author_facet | Shugaev, Maxim V. Hoque, Md Reshad Ul Kennedy, Bridget Riley, Joseph T. Hwang, Fiona Hagen, Justin Ghuman, Harvir Garcia-O'Donnell, Ethan Qadri, Syed Noor Santiago, Freddie Lee, Mun Wai |
| contents | Video sequence capturing through refractive dynamic media, such as a turbulent air or water surface, often suffer from severe geometric distortions and temporal instability. While recent advances address mild atmospheric turbulence, no existing benchmarks systematically evaluate restoration methods under strong and highly nonuniform refractive conditions. We present a comprehensive benchmark for geometric distortion removal in video, covering a range from turbulence-like mild warping to strong discontinuous refractive deformations. The benchmark includes both laboratory-captured real data and synthetic sequences generated for static scenes via physics-based light refraction modeling across four distortion levels and multiple surface wave types. We evaluate a spectrum of methods from simple baselines and classical registration algorithms to advanced learning-based approaches including DATUM and our proposed diffusion based V-cache for high and extreme distortions regimes. Evaluation uses both pixel-level (PSNR, SSIM), and perceptual (LPIPS, DINO, CLIP) metrics providing the first large scale analysis of geometric distortion removal. Our benchmark establishes a new foundation for developing and evaluating algorithms capable of reconstructing video from highly distorted optical environments. Our code and datasets are available at https://github.com/iafoss/refractive-mfir-benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05079 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A unified Benchmark for Multi-Frame Image Restoration under Severe Refractive Warping Shugaev, Maxim V. Hoque, Md Reshad Ul Kennedy, Bridget Riley, Joseph T. Hwang, Fiona Hagen, Justin Ghuman, Harvir Garcia-O'Donnell, Ethan Qadri, Syed Noor Santiago, Freddie Lee, Mun Wai Computer Vision and Pattern Recognition I.4.3; I.4.4 Video sequence capturing through refractive dynamic media, such as a turbulent air or water surface, often suffer from severe geometric distortions and temporal instability. While recent advances address mild atmospheric turbulence, no existing benchmarks systematically evaluate restoration methods under strong and highly nonuniform refractive conditions. We present a comprehensive benchmark for geometric distortion removal in video, covering a range from turbulence-like mild warping to strong discontinuous refractive deformations. The benchmark includes both laboratory-captured real data and synthetic sequences generated for static scenes via physics-based light refraction modeling across four distortion levels and multiple surface wave types. We evaluate a spectrum of methods from simple baselines and classical registration algorithms to advanced learning-based approaches including DATUM and our proposed diffusion based V-cache for high and extreme distortions regimes. Evaluation uses both pixel-level (PSNR, SSIM), and perceptual (LPIPS, DINO, CLIP) metrics providing the first large scale analysis of geometric distortion removal. Our benchmark establishes a new foundation for developing and evaluating algorithms capable of reconstructing video from highly distorted optical environments. Our code and datasets are available at https://github.com/iafoss/refractive-mfir-benchmark. |
| title | A unified Benchmark for Multi-Frame Image Restoration under Severe Refractive Warping |
| topic | Computer Vision and Pattern Recognition I.4.3; I.4.4 |
| url | https://arxiv.org/abs/2605.05079 |