{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/deep-reparametrization-of-multi-frame-super","title":"Deep Reparametrization of Multi-Frame Super-Resolution and Denoising","arxiv_id":"2108.08286","date":"2021-08-18","proceeding":"ICCV 2021 10","authors":["Goutam Bhat","Martin Danelljan","Fisher Yu","Luc van Gool","Radu Timofte"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2108.08286v1","url_pdf":"https://arxiv.org/pdf/2108.08286v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-reparametrization-of-multi-frame-super","repo_url":"https://github.com/goutamgmb/deep-burst-sr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reparametrization-of-multi-frame-super","repo_url":"https://github.com/goutamgmb/deep-rep","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"burst-image-super-resolution","task_name":"Burst Image Super-Resolution"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"multi-frame-super-resolution","task_name":"Multi-Frame Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/burst-image-super-resolution-on-burstsr","task":"Burst Image Super-Resolution","dataset":"BurstSR","model":"MFIR","rank_in_archive_order":6,"of":9,"metrics":{"LPIPS":"0.023","PSNR":"48.33","SSIM":"0.985"},"uses_additional_data":false},{"leaderboard":"/sota/burst-image-super-resolution-on","task":"Burst Image Super-Resolution","dataset":"SyntheticBurst","model":"MFIR","rank_in_archive_order":7,"of":8,"metrics":{"LPIPS":"0.045","PSNR":"41.56","SSIM":"0.964"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.08286","atlas_url":"https://app.syntology.ai/?focus=2108.08286","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2108.08286"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2108.08286\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2108.08286"},"call":"get_concepts_for_paper(arxiv_id=\"2108.08286\")"}],"by_repo":[{"repo":"goutamgmb/deep-burst-sr","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2101.10997"],"harvested_for_calls":[{"arxiv_id":"2101.10997","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2101.10997"},"call":"get_harvested_code_for_paper(arxiv_id=\"2101.10997\")"}]},{"repo":"goutamgmb/deep-rep","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2101.10997"],"harvested_for_calls":[{"arxiv_id":"2101.10997","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2101.10997"},"call":"get_harvested_code_for_paper(arxiv_id=\"2101.10997\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"fb8a0be176223b8c77aa55510a6eada46b4a2fff9f4fade07824e115bad7c3b0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}