{"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/semantic-guided-zero-shot-learning-for-low","title":"Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement","arxiv_id":"2110.00970","date":"2021-10-03","proceeding":null,"authors":["Shen Zheng","Gaurav Gupta"],"abstract":"Low-light images challenge both human perceptions and computer vision algorithms. It is crucial to make algorithms robust to enlighten low-light images for computational photography and computer vision applications such as real-time detection and segmentation. This paper proposes a semantic-guided zero-shot low-light enhancement network (SGZ) which is trained in the absence of paired images, unpaired datasets, and segmentation annotation. Firstly, we design an enhancement factor extraction network using depthwise separable convolution for an efficient estimate of the pixel-wise light deficiency of an low-light image. Secondly, we propose a recurrent image enhancement network to progressively enhance the low-light image with affordable model size. Finally, we introduce an unsupervised semantic segmentation network for preserving the semantic information during intensive enhancement. Extensive experiments on benchmark datasets and a low-light video demonstrate that our model outperforms the previous state-of-the-art. We further discuss the benefits of the proposed method for low-light detection and segmentation. Code is available at https://github.com/ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement","url_abs":"https://arxiv.org/abs/2110.00970v4","url_pdf":"https://arxiv.org/pdf/2110.00970v4.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":"semantic-guided-zero-shot-learning-for-low","repo_url":"https://github.com/ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"low-light-image-enhancement","task_name":"Low-Light Image Enhancement"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-semantic-segmentation","task_name":"Unsupervised Semantic Segmentation"},{"task_slug":"video-enhancement","task_name":"Video Enhancement"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.00970","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00970"}},"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/ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"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":"5741d6f9ffbbe0e5","entry":"cal_fps","repo":"ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement","repo_kind":"official","path":"demo/make_video.py","file_url":"https://github.com/ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement/blob/HEAD/demo/make_video.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":"5741d6f9ffbbe0e5"}},{"code_sha256_prefix":"d49b0c53ed3eb4f4","entry":"get_NoGT_target","repo":"ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement","repo_kind":"official","path":"modeling/fpn.py","file_url":"https://github.com/ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement/blob/HEAD/modeling/fpn.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":"d49b0c53ed3eb4f4"}},{"code_sha256_prefix":"3a519afa10c97538","entry":"image_from_path","repo":"ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement/blob/HEAD/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":"3a519afa10c97538"}},{"code_sha256_prefix":"c7aea909c128d085","entry":"one_hot","repo":"ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement","repo_kind":"official","path":"modeling/fpn.py","file_url":"https://github.com/ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement/blob/HEAD/modeling/fpn.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":"c7aea909c128d085"}},{"code_sha256_prefix":"8ff82cf6196bd377","entry":"populate_train_list","repo":"ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement","repo_kind":"official","path":"dataloader.py","file_url":"https://github.com/ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement/blob/HEAD/dataloader.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":"8ff82cf6196bd377"}},{"code_sha256_prefix":"fdbd04b290b58b1a","entry":"resize_target","repo":"ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement","repo_kind":"official","path":"modeling/fpn.py","file_url":"https://github.com/ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement/blob/HEAD/modeling/fpn.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":"fdbd04b290b58b1a"}},{"code_sha256_prefix":"c7423f05f117cdcb","entry":"resnet101","repo":"ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement","repo_kind":"official","path":"modeling/resnet.py","file_url":"https://github.com/ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement/blob/HEAD/modeling/resnet.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":"c7423f05f117cdcb"}},{"code_sha256_prefix":"8d58c0005a32eac6","entry":"resnet50","repo":"ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement","repo_kind":"official","path":"modeling/resnet.py","file_url":"https://github.com/ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement/blob/HEAD/modeling/resnet.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":"8d58c0005a32eac6"}},{"code_sha256_prefix":"f250baa6283b7e00","entry":"scale_image","repo":"ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ShenZheng2000/Semantic-Guided-Low-Light-Image-Enhancement/blob/HEAD/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":"f250baa6283b7e00"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}