{"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/correlation-matching-transformation","title":"Correlation Matching Transformation Transformers for UHD Image Restoration","arxiv_id":"2406.00629","date":"2024-06-02","proceeding":null,"authors":["Cong Wang","Jinshan Pan","Wei Wang","Gang Fu","Siyuan Liang","Mengzhu Wang","Xiao-Ming Wu","Jun Liu"],"abstract":"This paper proposes UHDformer, a general Transformer for Ultra-High-Definition (UHD) image restoration. UHDformer contains two learning spaces: (a) learning in high-resolution space and (b) learning in low-resolution space. The former learns multi-level high-resolution features and fuses low-high features and reconstructs the residual images, while the latter explores more representative features learning from the high-resolution ones to facilitate better restoration. To better improve feature representation in low-resolution space, we propose to build feature transformation from the high-resolution space to the low-resolution one. To that end, we propose two new modules: Dual-path Correlation Matching Transformation module (DualCMT) and Adaptive Channel Modulator (ACM). The DualCMT selects top C/r (r is greater or equal to 1 which controls the squeezing level) correlation channels from the max-pooling/mean-pooling high-resolution features to replace low-resolution ones in Transformers, which can effectively squeeze useless content to improve the feature representation in low-resolution space to facilitate better recovery. The ACM is exploited to adaptively modulate multi-level high-resolution features, enabling to provide more useful features to low-resolution space for better learning. Experimental results show that our UHDformer reduces about ninety-seven percent model sizes compared with most state-of-the-art methods while significantly improving performance under different training sets on 3 UHD image restoration tasks, including low-light image enhancement, image dehazing, and image deblurring. The source codes will be made available at https://github.com/supersupercong/UHDformer.","url_abs":"https://arxiv.org/abs/2406.00629v1","url_pdf":"https://arxiv.org/pdf/2406.00629v1.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":"correlation-matching-transformation","repo_url":"https://github.com/supersupercong/uhdformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"},{"task_slug":"image-dehazing","task_name":"Image Dehazing"},{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"low-light-image-enhancement","task_name":"Low-Light Image Enhancement"}],"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":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.00629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00629"}},"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/supersupercong/uhdformer","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/supersupercong/UHDformer","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_fixture":2,"ran":7,"ran_honours":2,"ran_draft_wrong":3,"unverified":5},"by_repo_kind":{"official":{"samples":18,"ran":13,"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":19,"samples":[{"code_sha256_prefix":"144d10b49baeb8a6","entry":"window_partition","repo":"supersupercong/uhdformer","repo_kind":"official","path":"basicsr/archs/network_swinir.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/basicsr/archs/network_swinir.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"7768e2df71a905ea","entry":"Matching","repo":"supersupercong/UHDformer","repo_kind":"official","path":"basicsr/archs/femasr_arch.py","file_url":"https://github.com/supersupercong/UHDformer/blob/HEAD/basicsr/archs/femasr_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7768e2df71a905ea"}},{"code_sha256_prefix":"bc51e42faf58567f","entry":"Matching_transformation","repo":"supersupercong/UHDformer","repo_kind":"official","path":"basicsr/archs/femasr_arch.py","file_url":"https://github.com/supersupercong/UHDformer/blob/HEAD/basicsr/archs/femasr_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bc51e42faf58567f"}},{"code_sha256_prefix":"1345f4fc63011f70","entry":"batched_index_select","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"1345f4fc63011f70"}},{"code_sha256_prefix":"41c726254f92759d","entry":"calculate_weights_indices","repo":"supersupercong/uhdformer","repo_kind":"official","path":"comput_psnr_ssim.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/comput_psnr_ssim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"41c726254f92759d"}},{"code_sha256_prefix":"6154e3744ece5728","entry":"create_window","repo":"supersupercong/uhdformer","repo_kind":"official","path":"basicsr/models/cal_ssim.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/basicsr/models/cal_ssim.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6154e3744ece5728"}},{"code_sha256_prefix":"2a78a7db11a55ede","entry":"cubic","repo":"supersupercong/uhdformer","repo_kind":"official","path":"comput_psnr_ssim.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/comput_psnr_ssim.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2a78a7db11a55ede"}},{"code_sha256_prefix":"5cf7893d7b439f34","entry":"equalize_hist_color","repo":"supersupercong/uhdformer","repo_kind":"official","path":"inference_uhdformer.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/inference_uhdformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5cf7893d7b439f34"}},{"code_sha256_prefix":"c56b7ef16f309a45","entry":"gaussian","repo":"supersupercong/uhdformer","repo_kind":"official","path":"basicsr/models/cal_ssim.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/basicsr/models/cal_ssim.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c56b7ef16f309a45"}},{"code_sha256_prefix":"25d2b867e5ed26b3","entry":"get_residue_structure_mean","repo":"supersupercong/uhdformer","repo_kind":"official","path":"inference_uhdformer.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/inference_uhdformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"25d2b867e5ed26b3"}},{"code_sha256_prefix":"a418150375355db5","entry":"imresize","repo":"supersupercong/uhdformer","repo_kind":"official","path":"comput_psnr_ssim.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/comput_psnr_ssim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a418150375355db5"}},{"code_sha256_prefix":"138161515f1d0419","entry":"neirest_neighbores","repo":"supersupercong/UHDformer","repo_kind":"official","path":"basicsr/archs/femasr_arch.py","file_url":"https://github.com/supersupercong/UHDformer/blob/HEAD/basicsr/archs/femasr_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"138161515f1d0419"}},{"code_sha256_prefix":"d51cded6ddd608db","entry":"neirest_neighbores_on_l2","repo":"supersupercong/UHDformer","repo_kind":"official","path":"basicsr/archs/femasr_arch.py","file_url":"https://github.com/supersupercong/UHDformer/blob/HEAD/basicsr/archs/femasr_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d51cded6ddd608db"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"supersupercong/uhdformer","repo_kind":"official","path":"basicsr/archs/network_swinir.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/basicsr/archs/network_swinir.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"7ab32da4188a2275","entry":"check_image_size","repo":"supersupercong/uhdformer","repo_kind":"official","path":"inference_uhdformer.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/inference_uhdformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7ab32da4188a2275"}},{"code_sha256_prefix":"a648a03a952822c0","entry":"reduce_loss","repo":"supersupercong/uhdformer","repo_kind":"official","path":"basicsr/losses/loss_util.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/basicsr/losses/loss_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a648a03a952822c0"}},{"code_sha256_prefix":"9151c793f90473f0","entry":"ssim","repo":"supersupercong/uhdformer","repo_kind":"official","path":"basicsr/models/cal_ssim.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/basicsr/models/cal_ssim.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9151c793f90473f0"}},{"code_sha256_prefix":"1ba39317ea81871a","entry":"weight_reduce_loss","repo":"supersupercong/uhdformer","repo_kind":"official","path":"basicsr/losses/loss_util.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/basicsr/losses/loss_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1ba39317ea81871a"}},{"code_sha256_prefix":"cf63f8afc13f62a7","entry":"weighted_loss","repo":"supersupercong/uhdformer","repo_kind":"official","path":"basicsr/losses/loss_util.py","file_url":"https://github.com/supersupercong/uhdformer/blob/HEAD/basicsr/losses/loss_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cf63f8afc13f62a7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}