Deep Reparametrization of Multi-Frame Super-Resolution and Denoising

We propose a deep reparametrization of the maximum a posteriori formulation commonly employed in multi-frame image restoration tasks. Our approach is derived by introducing a learned error metric and a latent representation of the target image, which transforms the MAP objective to a deep feature space. The deep reparametrization allows us to directly model the image formation process in the latent space, and to integrate learned image priors into the prediction. Our approach thereby leverages the advantages of deep learning, while also benefiting from the principled multi-frame fusion provided by the classical MAP formulation. We validate our approach through comprehensive experiments on burst denoising and burst super-resolution datasets. Our approach sets a new state-of-the-art for both tasks, demonstrating the generality and effectiveness of the proposed formulation.

PDF Abstract ICCV 2021 PDF ICCV 2021 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Burst Image Super-Resolution BurstSR MFIR PSNR 48.33 # 4
SSIM 0.985 # 3
LPIPS 0.023 # 4
Burst Image Super-Resolution SyntheticBurst MFIR PSNR 41.56 # 5
SSIM 0.964 # 4
LPIPS 0.045 # 2

Methods


No methods listed for this paper. Add relevant methods here