A unified Benchmark for Multi-Frame Image Restoration under Severe Refractive Warping
For researchers in video restoration and computational imaging, this benchmark fills a gap by systematically evaluating methods under strong refractive distortions, but it is an incremental contribution as it primarily provides a dataset and evaluation framework.
This paper introduces a benchmark for multi-frame image restoration under severe refractive warping, covering mild to extreme distortions with real and synthetic data. Evaluation of methods including a proposed diffusion-based V-cache shows that severe distortions remain challenging, with the benchmark providing a foundation for future algorithm development.
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.