Papers › Deep Reparametrization of Multi-Frame Super-Resolution and Denoising

Deep Reparametrization of Multi-Frame Super-Resolution and Denoising

18 Aug 2021ICCV 2021 10arXiv:2108.08286archive 2025-07-28

Goutam Bhat, Martin Danelljan, Fisher Yu, Luc van Gool, Radu Timofte

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.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

goutamgmb/deep-burst-sr mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Burst Super-Resolution (arXiv:2101.10997; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
goutamgmb/deep-rep mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Burst Super-Resolution (arXiv:2101.10997; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Burst Image Super-ResolutionDenoisingImage RestorationMulti-Frame Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Burst Image Super-Resolution BurstSR MFIR LPIPS 0.023 #6 of 9 Archive leaderboard report
Burst Image Super-Resolution BurstSR MFIR PSNR 48.33 #6 of 9 Archive leaderboard report
Burst Image Super-Resolution BurstSR MFIR SSIM 0.985 #6 of 9 Archive leaderboard report
Burst Image Super-Resolution SyntheticBurst MFIR LPIPS 0.045 #7 of 8 Archive leaderboard report
Burst Image Super-Resolution SyntheticBurst MFIR PSNR 41.56 #7 of 8 Archive leaderboard report
Burst Image Super-Resolution SyntheticBurst MFIR SSIM 0.964 #7 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections