{"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/cascadedgaze-efficiency-in-global-context","title":"CascadedGaze: Efficiency in Global Context Extraction for Image Restoration","arxiv_id":"2401.15235","date":"2024-01-26","proceeding":null,"authors":["Amirhosein Ghasemabadi","Muhammad Kamran Janjua","Mohammad Salameh","Chunhua Zhou","Fengyu Sun","Di Niu"],"abstract":"Image restoration tasks traditionally rely on convolutional neural networks. However, given the local nature of the convolutional operator, they struggle to capture global information. The promise of attention mechanisms in Transformers is to circumvent this problem, but it comes at the cost of intensive computational overhead. Many recent studies in image restoration have focused on solving the challenge of balancing performance and computational cost via Transformer variants. In this paper, we present CascadedGaze Network (CGNet), an encoder-decoder architecture that employs Global Context Extractor (GCE), a novel and efficient way to capture global information for image restoration. The GCE module leverages small kernels across convolutional layers to learn global dependencies, without requiring self-attention. Extensive experimental results show that our computationally efficient approach performs competitively to a range of state-of-the-art methods on synthetic image denoising and single image deblurring tasks, and pushes the performance boundary further on the real image denoising task.","url_abs":"https://arxiv.org/abs/2401.15235v2","url_pdf":"https://arxiv.org/pdf/2401.15235v2.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":"cascadedgaze-efficiency-in-global-context","repo_url":"https://github.com/Ascend-Research/CascadedGaze","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"single-image-deblurring","task_name":"Single Image Deblurring"}],"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-deblurring-on-gopro","task":"Image Deblurring","dataset":"GoPro","model":"CGNet","rank_in_archive_order":13,"of":55,"metrics":{"PSNR":"33.77","SSIM":"0.968"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-sidd","task":"Image Denoising","dataset":"SIDD","model":"CGNet","rank_in_archive_order":1,"of":22,"metrics":{"PSNR (sRGB)":"40.39","SSIM (sRGB)":"0.964"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2401.15235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15235"}},"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/Ascend-Research/CascadedGaze","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":11,"ran":10,"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":"1d7ce6d6dd7ff5c1","entry":"calculate_fid","repo":"Ascend-Research/CascadedGaze","repo_kind":"official","path":"basicsr/metrics/fid.py","file_url":"https://github.com/Ascend-Research/CascadedGaze/blob/HEAD/basicsr/metrics/fid.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":"1d7ce6d6dd7ff5c1"}},{"code_sha256_prefix":"5170ff1c4106b27a","entry":"compute_feature","repo":"Ascend-Research/CascadedGaze","repo_kind":"official","path":"basicsr/metrics/niqe.py","file_url":"https://github.com/Ascend-Research/CascadedGaze/blob/HEAD/basicsr/metrics/niqe.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":"5170ff1c4106b27a"}},{"code_sha256_prefix":"a1282a48b0941f5d","entry":"estimate_aggd_param","repo":"Ascend-Research/CascadedGaze","repo_kind":"official","path":"basicsr/metrics/niqe.py","file_url":"https://github.com/Ascend-Research/CascadedGaze/blob/HEAD/basicsr/metrics/niqe.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":"a1282a48b0941f5d"}},{"code_sha256_prefix":"c9fb213c957dc82d","entry":"extract_inception_features","repo":"Ascend-Research/CascadedGaze","repo_kind":"official","path":"basicsr/metrics/fid.py","file_url":"https://github.com/Ascend-Research/CascadedGaze/blob/HEAD/basicsr/metrics/fid.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":"c9fb213c957dc82d"}},{"code_sha256_prefix":"ef9faf68f492a375","entry":"flow_warp","repo":"Ascend-Research/CascadedGaze","repo_kind":"official","path":"basicsr/models/archs/arch_util.py","file_url":"https://github.com/Ascend-Research/CascadedGaze/blob/HEAD/basicsr/models/archs/arch_util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef9faf68f492a375"}},{"code_sha256_prefix":"cd569444547de84f","entry":"get_position_from_periods","repo":"Ascend-Research/CascadedGaze","repo_kind":"official","path":"basicsr/models/lr_scheduler.py","file_url":"https://github.com/Ascend-Research/CascadedGaze/blob/HEAD/basicsr/models/lr_scheduler.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd569444547de84f"}},{"code_sha256_prefix":"96ad5dc9ca239aec","entry":"make_layer","repo":"Ascend-Research/CascadedGaze","repo_kind":"official","path":"basicsr/models/archs/arch_util.py","file_url":"https://github.com/Ascend-Research/CascadedGaze/blob/HEAD/basicsr/models/archs/arch_util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"96ad5dc9ca239aec"}},{"code_sha256_prefix":"95c6eba9350a455a","entry":"prepare_for_ssim","repo":"Ascend-Research/CascadedGaze","repo_kind":"official","path":"basicsr/metrics/psnr_ssim.py","file_url":"https://github.com/Ascend-Research/CascadedGaze/blob/HEAD/basicsr/metrics/psnr_ssim.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95c6eba9350a455a"}},{"code_sha256_prefix":"95067518dc16b3e5","entry":"reorder_image","repo":"Ascend-Research/CascadedGaze","repo_kind":"official","path":"basicsr/metrics/metric_util.py","file_url":"https://github.com/Ascend-Research/CascadedGaze/blob/HEAD/basicsr/metrics/metric_util.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":"95067518dc16b3e5"}},{"code_sha256_prefix":"5a1d8458dc7077a6","entry":"resize_flow","repo":"Ascend-Research/CascadedGaze","repo_kind":"official","path":"basicsr/models/archs/arch_util.py","file_url":"https://github.com/Ascend-Research/CascadedGaze/blob/HEAD/basicsr/models/archs/arch_util.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":"5a1d8458dc7077a6"}},{"code_sha256_prefix":"0029cb1566e47350","entry":"niqe","repo":"Ascend-Research/CascadedGaze","repo_kind":"official","path":"basicsr/metrics/niqe.py","file_url":"https://github.com/Ascend-Research/CascadedGaze/blob/HEAD/basicsr/metrics/niqe.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":"0029cb1566e47350"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}