{"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/drct-saving-image-super-resolution-away-from","title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","arxiv_id":"2404.00722","date":"2024-03-31","proceeding":null,"authors":["Chih-Chung Hsu","Chia-Ming Lee","Yi-Shiuan Chou"],"abstract":"In recent years, Vision Transformer-based approaches for low-level vision tasks have achieved widespread success. Unlike CNN-based models, Transformers are more adept at capturing long-range dependencies, enabling the reconstruction of images utilizing non-local information. In the domain of super-resolution, Swin-transformer-based models have become mainstream due to their capability of global spatial information modeling and their shifting-window attention mechanism that facilitates the interchange of information between different windows. Many researchers have enhanced model performance by expanding the receptive fields or designing meticulous networks, yielding commendable results. However, we observed that it is a general phenomenon for the feature map intensity to be abruptly suppressed to small values towards the network's end. This implies an information bottleneck and a diminishment of spatial information, implicitly limiting the model's potential. To address this, we propose the Dense-residual-connected Transformer (DRCT), aimed at mitigating the loss of spatial information and stabilizing the information flow through dense-residual connections between layers, thereby unleashing the model's potential and saving the model away from information bottleneck. Experiment results indicate that our approach surpasses state-of-the-art methods on benchmark datasets and performs commendably at the NTIRE-2024 Image Super-Resolution (x4) Challenge. Our source code is available at https://github.com/ming053l/DRCT","url_abs":"https://arxiv.org/abs/2404.00722v5","url_pdf":"https://arxiv.org/pdf/2404.00722v5.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":"drct-saving-image-super-resolution-away-from","repo_url":"https://github.com/ming053l/drct","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"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":[{"leaderboard":"/sota/image-super-resolution-on-bsd100-2x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 2x upscaling","model":"DRCT-L","rank_in_archive_order":3,"of":30,"metrics":{"PSNR":"32.90","SSIM":"0.9078"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-2x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 2x upscaling","model":"DRCT","rank_in_archive_order":6,"of":30,"metrics":{"PSNR":"32.75","SSIM":"0.9071"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-4x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 4x upscaling","model":"DRCT-L","rank_in_archive_order":1,"of":71,"metrics":{"PSNR":"28.16","SSIM":"0.7577"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-4x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 4x upscaling","model":"DRCT","rank_in_archive_order":6,"of":71,"metrics":{"PSNR":"28.06","SSIM":"0.7533"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-2x","task":"Image Super-Resolution","dataset":"Manga109 - 2x upscaling","model":"DRCT-L","rank_in_archive_order":2,"of":21,"metrics":{"PSNR":"41.14","SSIM":"0.9842"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-2x","task":"Image Super-Resolution","dataset":"Manga109 - 2x upscaling","model":"DRCT","rank_in_archive_order":10,"of":21,"metrics":{"PSNR":"40.41","SSIM":"0.9814"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-4x","task":"Image Super-Resolution","dataset":"Manga109 - 4x upscaling","model":"DRCT-L","rank_in_archive_order":2,"of":50,"metrics":{"PSNR":"33.14","SSIM":"0.9347"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-4x","task":"Image Super-Resolution","dataset":"Manga109 - 4x upscaling","model":"DRCT","rank_in_archive_order":5,"of":50,"metrics":{"PSNR":"32.96","SSIM":"0.9324"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-2x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 2x upscaling","model":"DRCT-L","rank_in_archive_order":1,"of":35,"metrics":{"PSNR":"35.36","SSIM":"0.9302"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-2x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 2x upscaling","model":"DRCT","rank_in_archive_order":8,"of":35,"metrics":{"PSNR":"34.96","SSIM":"0.9287"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"DRCT-L","rank_in_archive_order":1,"of":104,"metrics":{"PSNR":"29.54","SSIM":"0.8025"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"DRCT","rank_in_archive_order":6,"of":104,"metrics":{"PSNR":"29.40","SSIM":"0.8003"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-2x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 2x upscaling","model":"DRCT-L","rank_in_archive_order":1,"of":41,"metrics":{"PSNR":"39.14","SSIM":"0.9658"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-2x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 2x upscaling","model":"DRCT","rank_in_archive_order":7,"of":41,"metrics":{"PSNR":"38.72","SSIM":"0.9646"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-3x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 3x upscaling","model":"DRCT-L","rank_in_archive_order":2,"of":32,"metrics":{"PSNR":"35.32","SSIM":"0.9348"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-3x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 3x upscaling","model":"DRCT","rank_in_archive_order":7,"of":32,"metrics":{"PSNR":"35.18","SSIM":"0.9338"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-2x","task":"Image Super-Resolution","dataset":"Urban100 - 2x upscaling","model":"DRCT-L","rank_in_archive_order":2,"of":29,"metrics":{"PSNR":"35.17","SSIM":"0.9516"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-2x","task":"Image Super-Resolution","dataset":"Urban100 - 2x upscaling","model":"DRCT","rank_in_archive_order":10,"of":29,"metrics":{"PSNR":"34.54","SSIM":"0.9474"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","task":"Image Super-Resolution","dataset":"Urban100 - 4x upscaling","model":"DRCT-L","rank_in_archive_order":2,"of":65,"metrics":{"PSNR":"28.70","SSIM":"0.8508"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","task":"Image Super-Resolution","dataset":"Urban100 - 4x upscaling","model":"DRCT","rank_in_archive_order":6,"of":65,"metrics":{"PSNR":"28.40","SSIM":"0.8457"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.00722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00722"}},"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/ming053l/drct","reach":null}],"summary":{"ran_fixture":2,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":1,"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":3,"samples":[{"code_sha256_prefix":"52d96aa31ed74a56","entry":"drop_path","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":"52d96aa31ed74a56"}},{"code_sha256_prefix":"8b9d78de0f2e7f75","entry":"test","repo":"ming053l/drct","repo_kind":"official","path":"inference.py","file_url":"https://github.com/ming053l/drct/blob/HEAD/inference.py","link_basis":"first_harvest_node","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":"8b9d78de0f2e7f75"}},{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","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":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f9fd6241d935f07b"}},{"code_sha256_prefix":"fb32094c6dbece71","entry":"window_reverse","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fb32094c6dbece71"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}