{"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/activating-more-pixels-in-image-super","title":"Activating More Pixels in Image Super-Resolution Transformer","arxiv_id":"2205.04437","date":"2022-05-09","proceeding":"CVPR 2023 1","authors":["Xiangyu Chen","Xintao Wang","Jiantao Zhou","Yu Qiao","Chao Dong"],"abstract":"Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB. Codes and models are available at https://github.com/XPixelGroup/HAT.","url_abs":"https://arxiv.org/abs/2205.04437v3","url_pdf":"https://arxiv.org/pdf/2205.04437v3.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":"activating-more-pixels-in-image-super","repo_url":"https://github.com/chxy95/hat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"activating-more-pixels-in-image-super","repo_url":"https://github.com/xpixelgroup/hat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"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":"HAT-L","rank_in_archive_order":7,"of":30,"metrics":{"PSNR":"32.74","SSIM":"0.9066"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-2x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 2x upscaling","model":"HAT","rank_in_archive_order":9,"of":30,"metrics":{"PSNR":"32.69","SSIM":"0.9060"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-3x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 3x upscaling","model":"HAT-L","rank_in_archive_order":3,"of":21,"metrics":{"PSNR":"29.63","SSIM":"0.8191"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-3x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 3x upscaling","model":"HAT","rank_in_archive_order":5,"of":21,"metrics":{"PSNR":"29.59","SSIM":"0.8177"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-4x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 4x upscaling","model":"HAT-L","rank_in_archive_order":4,"of":71,"metrics":{"PSNR":"28.09","SSIM":"0.7551"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-bsd100-4x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 4x upscaling","model":"HAT","rank_in_archive_order":8,"of":71,"metrics":{"PSNR":"28.05","SSIM":"0.7534"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-2x","task":"Image Super-Resolution","dataset":"Manga109 - 2x upscaling","model":"HAT-L","rank_in_archive_order":4,"of":21,"metrics":{"PSNR":"41.01","SSIM":"0.9831"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-2x","task":"Image Super-Resolution","dataset":"Manga109 - 2x upscaling","model":"HAT","rank_in_archive_order":6,"of":21,"metrics":{"PSNR":"40.71","SSIM":"0.9819"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-3x","task":"Image Super-Resolution","dataset":"Manga109 - 3x upscaling","model":"HAT-L","rank_in_archive_order":3,"of":17,"metrics":{"PSNR":"36.02","SSIM":"0.9576"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-3x","task":"Image Super-Resolution","dataset":"Manga109 - 3x upscaling","model":"HAT","rank_in_archive_order":5,"of":17,"metrics":{"PSNR":"35.84","SSIM":"0.9567"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-4x","task":"Image Super-Resolution","dataset":"Manga109 - 4x upscaling","model":"HAT-L","rank_in_archive_order":4,"of":50,"metrics":{"PSNR":"33.09","SSIM":"0.9335"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-4x","task":"Image Super-Resolution","dataset":"Manga109 - 4x upscaling","model":"HAT","rank_in_archive_order":6,"of":50,"metrics":{"PSNR":"32.87","SSIM":"0.9319"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-2x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 2x upscaling","model":"HAT-L","rank_in_archive_order":3,"of":35,"metrics":{"PSNR":"35.29","SSIM":"0.9293"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-2x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 2x upscaling","model":"HAT","rank_in_archive_order":6,"of":35,"metrics":{"PSNR":"35.13","SSIM":"0.9282"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-3x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 3x upscaling","model":"HAT-L","rank_in_archive_order":3,"of":24,"metrics":{"PSNR":"31.47","SSIM":"0.8584"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-3x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 3x upscaling","model":"HAT","rank_in_archive_order":5,"of":24,"metrics":{"PSNR":"31.33","SSIM":"0.8576"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"HAT-L","rank_in_archive_order":4,"of":104,"metrics":{"PSNR":"29.47","SSIM":"0.8015"},"uses_additional_data":true},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"HAT","rank_in_archive_order":7,"of":104,"metrics":{"PSNR":"29.38","SSIM":"0.8001"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-2x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 2x upscaling","model":"HAT-L","rank_in_archive_order":3,"of":41,"metrics":{"PSNR":"38.91","SSIM":"0.9646"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-2x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 2x upscaling","model":"HAT","rank_in_archive_order":6,"of":41,"metrics":{"PSNR":"38.73","SSIM":"0.9637"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-3x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 3x upscaling","model":"HAT-L","rank_in_archive_order":3,"of":32,"metrics":{"PSNR":"35.28","SSIM":"0.9345"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-3x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 3x upscaling","model":"HAT","rank_in_archive_order":8,"of":32,"metrics":{"PSNR":"35.16","SSIM":"0.9335"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-4x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 4x upscaling","model":"HAT-L","rank_in_archive_order":2,"of":12,"metrics":{"PSNR":"33.30","SSIM":"0.9083"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-2x","task":"Image Super-Resolution","dataset":"Urban100 - 2x upscaling","model":"HAT-L","rank_in_archive_order":4,"of":29,"metrics":{"PSNR":"35.09","SSIM":"0.9505"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-2x","task":"Image Super-Resolution","dataset":"Urban100 - 2x upscaling","model":"HAT","rank_in_archive_order":7,"of":29,"metrics":{"PSNR":"34.81","SSIM":"0.9489"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-3x","task":"Image Super-Resolution","dataset":"Urban100 - 3x upscaling","model":"HAT-L","rank_in_archive_order":3,"of":22,"metrics":{"PSNR":"30.92","SSIM":"0.8981"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-3x","task":"Image Super-Resolution","dataset":"Urban100 - 3x upscaling","model":"HAT","rank_in_archive_order":5,"of":22,"metrics":{"PSNR":"30.70","SSIM":"0.8949"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","task":"Image Super-Resolution","dataset":"Urban100 - 4x upscaling","model":"HAT-L","rank_in_archive_order":4,"of":65,"metrics":{"PSNR":"28.60","SSIM":"0.8498"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","task":"Image Super-Resolution","dataset":"Urban100 - 4x upscaling","model":"HAT","rank_in_archive_order":7,"of":65,"metrics":{"PSNR":"28.37","SSIM":"0.8447"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.04437","atlas_url":"https://app.syntology.ai/?focus=2205.04437","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":"2205.04437"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.04437\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.04437"},"call":"get_concepts_for_paper(arxiv_id=\"2205.04437\")"}],"by_repo":[{"repo":"chxy95/hat","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2309.05239"],"harvested_for_calls":[{"arxiv_id":"2309.05239","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.05239"},"call":"get_harvested_code_for_paper(arxiv_id=\"2309.05239\")"}]},{"repo":"xpixelgroup/hat","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"a225d446c8992815db6d3ec6560b3837bc0ecbecd9ff48f09fa64284261ded9e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}