{"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/u-shape-transformer-for-underwater-image","title":"U-shape Transformer for Underwater Image Enhancement","arxiv_id":"2111.11843","date":"2021-11-23","proceeding":null,"authors":["Lintao Peng","Chunli Zhu","Liheng Bian"],"abstract":"The light absorption and scattering of underwater impurities lead to poor underwater imaging quality. The existing data-driven based underwater image enhancement (UIE) techniques suffer from the lack of a large-scale dataset containing various underwater scenes and high-fidelity reference images. Besides, the inconsistent attenuation in different color channels and space areas is not fully considered for boosted enhancement. In this work, we constructed a large-scale underwater image (LSUI) dataset including 5004 image pairs, and reported an U-shape Transformer network where the transformer model is for the first time introduced to the UIE task. The U-shape Transformer is integrated with a channel-wise multi-scale feature fusion transformer (CMSFFT) module and a spatial-wise global feature modeling transformer (SGFMT) module, which reinforce the network's attention to the color channels and space areas with more serious attenuation. Meanwhile, in order to further improve the contrast and saturation, a novel loss function combining RGB, LAB and LCH color spaces is designed following the human vision principle. The extensive experiments on available datasets validate the state-of-the-art performance of the reported technique with more than 2dB superiority.","url_abs":"https://arxiv.org/abs/2111.11843v6","url_pdf":"https://arxiv.org/pdf/2111.11843v6.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":"u-shape-transformer-for-underwater-image","repo_url":"https://github.com/LintaoPeng/U-shape_Transformer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"u-shape-transformer-for-underwater-image","repo_url":"https://github.com/TingdiRen/URSCT-SESR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"uie","task_name":"UIE"},{"task_slug":"underwater-image-restoration","task_name":"Underwater Image Restoration"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[{"slug":"lsui","name":"LSUI","full_name":"Large Scale  Underwater Image Dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/underwater-image-restoration-on-lsui","task":"Underwater Image Restoration","dataset":"LSUI","model":"U-shape Transformer","rank_in_archive_order":2,"of":6,"metrics":{"PSNR":"24.16"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.11843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.11843"}},"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/LintaoPeng/U-shape_Transformer","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TingdiRen/URSCT-SESR","reach":null}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"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":"1391a8ffffc258ce","entry":"batch_PSNR","repo":"LintaoPeng/U-shape_Transformer","repo_kind":"official","path":"net/utils.py","file_url":"https://github.com/LintaoPeng/U-shape_Transformer/blob/HEAD/net/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1391a8ffffc258ce"}},{"code_sha256_prefix":"0b71fac5a3384432","entry":"data_augmentation","repo":"LintaoPeng/U-shape_Transformer","repo_kind":"official","path":"net/utils.py","file_url":"https://github.com/LintaoPeng/U-shape_Transformer/blob/HEAD/net/utils.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":"0b71fac5a3384432"}},{"code_sha256_prefix":"3abfd5ed3f8a1cf0","entry":"quantAB","repo":"LintaoPeng/U-shape_Transformer","repo_kind":"official","path":"utility/Qnt.py","file_url":"https://github.com/LintaoPeng/U-shape_Transformer/blob/HEAD/utility/Qnt.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":"3abfd5ed3f8a1cf0"}},{"code_sha256_prefix":"cdf3ade423488549","entry":"quantL","repo":"LintaoPeng/U-shape_Transformer","repo_kind":"official","path":"utility/Qnt.py","file_url":"https://github.com/LintaoPeng/U-shape_Transformer/blob/HEAD/utility/Qnt.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":"cdf3ade423488549"}},{"code_sha256_prefix":"a34b9a9bbbf4da8b","entry":"quantRGB","repo":"LintaoPeng/U-shape_Transformer","repo_kind":"official","path":"utility/Qnt.py","file_url":"https://github.com/LintaoPeng/U-shape_Transformer/blob/HEAD/utility/Qnt.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":"a34b9a9bbbf4da8b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}