{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/an-implicit-alignment-for-video-super","title":"Enhancing Video Super-Resolution via Implicit Resampling-based Alignment","arxiv_id":"2305.00163","date":"2023-04-29","proceeding":"CVPR 2024 1","authors":["Kai Xu","Ziwei Yu","Xin Wang","Michael Bi Mi","Angela Yao"],"abstract":"In video super-resolution, it is common to use a frame-wise alignment to support the propagation of information over time. The role of alignment is well-studied for low-level enhancement in video, but existing works overlook a critical step -- resampling. We show through extensive experiments that for alignment to be effective, the resampling should preserve the reference frequency spectrum while minimizing spatial distortions. However, most existing works simply use a default choice of bilinear interpolation for resampling even though bilinear interpolation has a smoothing effect and hinders super-resolution. From these observations, we propose an implicit resampling-based alignment. The sampling positions are encoded by a sinusoidal positional encoding, while the value is estimated with a coordinate network and a window-based cross-attention. We show that bilinear interpolation inherently attenuates high-frequency information while an MLP-based coordinate network can approximate more frequencies. Experiments on synthetic and real-world datasets show that alignment with our proposed implicit resampling enhances the performance of state-of-the-art frameworks with minimal impact on both compute and parameters.","url_abs":"https://arxiv.org/abs/2305.00163v2","url_pdf":"https://arxiv.org/pdf/2305.00163v2.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":"an-implicit-alignment-for-video-super","repo_url":"https://github.com/kai422/iart","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"video-super-resolution","task_name":"Video Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-super-resolution-on-reds4-4x-upscaling","task":"Video Super-Resolution","dataset":"REDS4- 4x upscaling","model":"IART","rank_in_archive_order":3,"of":7,"metrics":{"PSNR":"32.90","SSIM":"0.9138"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-vid4-4x-upscaling","task":"Video Super-Resolution","dataset":"Vid4 - 4x upscaling","model":"IART","rank_in_archive_order":3,"of":27,"metrics":{"PSNR":"28.26","SSIM":"0.8517"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.00163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00163"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kai422/iart","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"named_in_paper":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"52d96aa31ed74a56","entry":"drop_path","repo":"kai422/iart","repo_kind":"named_in_paper","path":"archs/psrt_sliding_arch.py","file_url":"https://github.com/kai422/iart/blob/HEAD/archs/psrt_sliding_arch.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52d96aa31ed74a56"}},{"code_sha256_prefix":"75fd6fbfca7a246c","entry":"window_reverse","repo":"kai422/iart","repo_kind":"named_in_paper","path":"archs/psrt_sliding_arch.py","file_url":"https://github.com/kai422/iart/blob/HEAD/archs/psrt_sliding_arch.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"75fd6fbfca7a246c"}},{"code_sha256_prefix":"e0f3c2fd11d92ad7","entry":"window_partition","repo":"kai422/iart","repo_kind":"named_in_paper","path":"archs/psrt_sliding_arch.py","file_url":"https://github.com/kai422/iart/blob/HEAD/archs/psrt_sliding_arch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e0f3c2fd11d92ad7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}