{"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/low-light-image-enhancement-with-wavelet","title":"Low-Light Image Enhancement with Wavelet-based Diffusion Models","arxiv_id":"2306.00306","date":"2023-06-01","proceeding":null,"authors":["Hai Jiang","Ao Luo","Songchen Han","Haoqiang Fan","Shuaicheng Liu"],"abstract":"Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. To address these issues, we propose a robust and efficient Diffusion-based Low-Light image enhancement approach, dubbed DiffLL. Specifically, we present a wavelet-based conditional diffusion model (WCDM) that leverages the generative power of diffusion models to produce results with satisfactory perceptual fidelity. Additionally, it also takes advantage of the strengths of wavelet transformation to greatly accelerate inference and reduce computational resource usage without sacrificing information. To avoid chaotic content and diversity, we perform both forward diffusion and denoising in the training phase of WCDM, enabling the model to achieve stable denoising and reduce randomness during inference. Moreover, we further design a high-frequency restoration module (HFRM) that utilizes the vertical and horizontal details of the image to complement the diagonal information for better fine-grained restoration. Extensive experiments on publicly available real-world benchmarks demonstrate that our method outperforms the existing state-of-the-art methods both quantitatively and visually, and it achieves remarkable improvements in efficiency compared to previous diffusion-based methods. In addition, we empirically show that the application for low-light face detection also reveals the latent practical values of our method. Code is available at https://github.com/JianghaiSCU/Diffusion-Low-Light.","url_abs":"https://arxiv.org/abs/2306.00306v3","url_pdf":"https://arxiv.org/pdf/2306.00306v3.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":"low-light-image-enhancement-with-wavelet","repo_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"face-detection","task_name":"Face Detection"},{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"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":"DiffLL","rank_in_archive_order":13,"of":40,"metrics":{"Average PSNR":"26.336","SSIM":"0.845"},"uses_additional_data":false},{"leaderboard":"/sota/low-light-image-enhancement-on-lolv2","task":"Low-Light Image Enhancement","dataset":"LOLv2","model":"DiffLL","rank_in_archive_order":4,"of":12,"metrics":{"Average PSNR":"28.86","SSIM":"0.876"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.00306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00306"}},"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/JianghaiSCU/Diffusion-Low-Light","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9,"ran_draft_wrong":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":13,"ran":12,"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":"d1da811331d9c0bc","entry":"Normalize","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/models/unet.py","link_basis":"plan_row","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":"d1da811331d9c0bc"}},{"code_sha256_prefix":"29b74807841606b3","entry":"Normalize","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"models/wavelet.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/models/wavelet.py","link_basis":"plan_row","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":"29b74807841606b3"}},{"code_sha256_prefix":"9215fb189fbfb9f4","entry":"compute_alpha","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"utils/sampling.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/utils/sampling.py","link_basis":"harvester_set","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":"9215fb189fbfb9f4"}},{"code_sha256_prefix":"1711055882a8cb05","entry":"data_transform","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"models/ddm.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/models/ddm.py","link_basis":"plan_row","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":"1711055882a8cb05"}},{"code_sha256_prefix":"bd1f17e427bf51a5","entry":"dict2namespace","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/evaluate.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd1f17e427bf51a5"}},{"code_sha256_prefix":"c772979b10e50aa7","entry":"dwt_init","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"models/wavelet.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/models/wavelet.py","link_basis":"plan_row","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":"c772979b10e50aa7"}},{"code_sha256_prefix":"ca0cea1ca1eeec89","entry":"get_beta_schedule","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"models/ddm.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/models/ddm.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca0cea1ca1eeec89"}},{"code_sha256_prefix":"111b7327d736b5ff","entry":"get_timestep_embedding","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/models/unet.py","link_basis":"plan_row","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":"111b7327d736b5ff"}},{"code_sha256_prefix":"444601dceca73c5e","entry":"inverse_data_transform","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"models/ddm.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/models/ddm.py","link_basis":"plan_row","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":"444601dceca73c5e"}},{"code_sha256_prefix":"fb592810ea948fbf","entry":"iwt_init","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"models/wavelet.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/models/wavelet.py","link_basis":"plan_row","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":"fb592810ea948fbf"}},{"code_sha256_prefix":"60c85826a345d8ed","entry":"load_checkpoint","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"utils/logging.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/utils/logging.py","link_basis":"plan_row","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":"60c85826a345d8ed"}},{"code_sha256_prefix":"607fa54d137fc5da","entry":"nonlinearity","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"models/unet.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/models/unet.py","link_basis":"plan_row","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":"607fa54d137fc5da"}},{"code_sha256_prefix":"261adf3e0143e77e","entry":"get_optimizer","repo":"JianghaiSCU/Diffusion-Low-Light","repo_kind":"official","path":"utils/optimize.py","file_url":"https://github.com/JianghaiSCU/Diffusion-Low-Light/blob/HEAD/utils/optimize.py","link_basis":"first_harvest_node","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":"261adf3e0143e77e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}