{"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/global-structure-aware-diffusion-process-for-1","title":"Global Structure-Aware Diffusion Process for Low-Light Image Enhancement","arxiv_id":"2310.17577","date":"2023-10-26","proceeding":"NeurIPS 2023 11","authors":["Jinhui Hou","Zhiyu Zhu","Junhui Hou","Hui Liu","Huanqiang Zeng","Hui Yuan"],"abstract":"This paper studies a diffusion-based framework to address the low-light image enhancement problem. To harness the capabilities of diffusion models, we delve into this intricate process and advocate for the regularization of its inherent ODE-trajectory. To be specific, inspired by the recent research that low curvature ODE-trajectory results in a stable and effective diffusion process, we formulate a curvature regularization term anchored in the intrinsic non-local structures of image data, i.e., global structure-aware regularization, which gradually facilitates the preservation of complicated details and the augmentation of contrast during the diffusion process. This incorporation mitigates the adverse effects of noise and artifacts resulting from the diffusion process, leading to a more precise and flexible enhancement. To additionally promote learning in challenging regions, we introduce an uncertainty-guided regularization technique, which wisely relaxes constraints on the most extreme regions of the image. Experimental evaluations reveal that the proposed diffusion-based framework, complemented by rank-informed regularization, attains distinguished performance in low-light enhancement. The outcomes indicate substantial advancements in image quality, noise suppression, and contrast amplification in comparison with state-of-the-art methods. We believe this innovative approach will stimulate further exploration and advancement in low-light image processing, with potential implications for other applications of diffusion models. The code is publicly available at https://github.com/jinnh/GSAD.","url_abs":"https://arxiv.org/abs/2310.17577v2","url_pdf":"https://arxiv.org/pdf/2310.17577v2.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":"global-structure-aware-diffusion-process-for-1","repo_url":"https://github.com/jinnh/GSAD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"low-light-image-enhancement","task_name":"Low-Light Image Enhancement"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/low-light-image-enhancement-on-lol","task":"Low-Light Image Enhancement","dataset":"LOL","model":"GlobalDiff","rank_in_archive_order":4,"of":40,"metrics":{"Average PSNR":"27.83","LPIPS":"0.091","SSIM":"0.877"},"uses_additional_data":false},{"leaderboard":"/sota/low-light-image-enhancement-on-lolv2","task":"Low-Light Image Enhancement","dataset":"LOLv2","model":"GlobalDiff","rank_in_archive_order":5,"of":12,"metrics":{"Average PSNR":"28.82","LPIPS":"0.095","SSIM":"0.895"},"uses_additional_data":false},{"leaderboard":"/sota/low-light-image-enhancement-on-lolv2-1","task":"Low-Light Image Enhancement","dataset":"LOLv2-synthetic","model":"GlobalDiff","rank_in_archive_order":7,"of":9,"metrics":{"Average PSNR":"28.67","LPIPS":"0.047","SSIM":"0.944"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.17577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17577"}},"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":"deterministic:regex_extraction","url":"https://github.com/jinnh/GSAD","reach":null}],"summary":{"ran":1},"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":1,"samples":[{"code_sha256_prefix":"601b775184504fef","entry":"GaussianDiffusion","repo":"jinnh/GSAD","repo_kind":"official","path":"model/ddpm_modules/diffusion.py","file_url":"https://github.com/jinnh/GSAD/blob/HEAD/model/ddpm_modules/diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"601b775184504fef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}