{"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/frequency-compensated-diffusion-model-for","title":"Frequency Compensated Diffusion Model for Real-scene Dehazing","arxiv_id":"2308.10510","date":"2023-08-21","proceeding":null,"authors":["Jing Wang","Songtao Wu","Kuanhong Xu","Zhiqiang Yuan"],"abstract":"Due to distribution shift, deep learning based methods for image dehazing suffer from performance degradation when applied to real-world hazy images. In this paper, we consider a dehazing framework based on conditional diffusion models for improved generalization to real haze. First, we find that optimizing the training objective of diffusion models, i.e., Gaussian noise vectors, is non-trivial. The spectral bias of deep networks hinders the higher frequency modes in Gaussian vectors from being learned and hence impairs the reconstruction of image details. To tackle this issue, we design a network unit, named Frequency Compensation block (FCB), with a bank of filters that jointly emphasize the mid-to-high frequencies of an input signal. We demonstrate that diffusion models with FCB achieve significant gains in both perceptual and distortion metrics. Second, to further boost the generalization performance, we propose a novel data synthesis pipeline, HazeAug, to augment haze in terms of degree and diversity. Within the framework, a solid baseline for blind dehazing is set up where models are trained on synthetic hazy-clean pairs, and directly generalize to real data. Extensive evaluations show that the proposed dehazing diffusion model significantly outperforms state-of-the-art methods on real-world images. Our code is at https://github.com/W-Jilly/frequency-compensated-diffusion-model-pytorch.","url_abs":"https://arxiv.org/abs/2308.10510v2","url_pdf":"https://arxiv.org/pdf/2308.10510v2.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":"frequency-compensated-diffusion-model-for","repo_url":"https://github.com/w-jilly/frequency-compensated-diffusion-model-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"frequency-compensated-diffusion-model-for","repo_url":"https://github.com/tianwenzhou/prodehaze","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-dehazing","task_name":"Image Dehazing"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.10510","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10510"}},"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/tianwenzhou/prodehaze","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/w-jilly/frequency-compensated-diffusion-model-pytorch","reach":null}],"summary":{"ran_fixture":3,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"listed":{"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":5,"samples":[{"code_sha256_prefix":"2bb46c5e4a7d9ff1","entry":"calc_mean_rgb","repo":"w-jilly/frequency-compensated-diffusion-model-pytorch","repo_kind":"official","path":"infer.py","file_url":"https://github.com/w-jilly/frequency-compensated-diffusion-model-pytorch/blob/HEAD/infer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2bb46c5e4a7d9ff1"}},{"code_sha256_prefix":"8241c0562bc710fd","entry":"chunk","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"8241c0562bc710fd"}},{"code_sha256_prefix":"8a6db4ba41f445c4","entry":"fix_img","repo":"w-jilly/frequency-compensated-diffusion-model-pytorch","repo_kind":"official","path":"infer.py","file_url":"https://github.com/w-jilly/frequency-compensated-diffusion-model-pytorch/blob/HEAD/infer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a6db4ba41f445c4"}},{"code_sha256_prefix":"4d4030148643ee3a","entry":"space_timesteps","repo":"tianwenzhou/prodehaze","repo_kind":"listed","path":"scripts/sr_val_ddpm_text_T_vqganfin_old.py","file_url":"https://github.com/tianwenzhou/prodehaze/blob/HEAD/scripts/sr_val_ddpm_text_T_vqganfin_old.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4d4030148643ee3a"}},{"code_sha256_prefix":"049882ee2ff7e3e5","entry":"GaussianDiffusion","repo":"w-jilly/frequency-compensated-diffusion-model-pytorch","repo_kind":"official","path":"model/dehaze_with_z_v2_modules/diffusion.py","file_url":"https://github.com/w-jilly/frequency-compensated-diffusion-model-pytorch/blob/HEAD/model/dehaze_with_z_v2_modules/diffusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"049882ee2ff7e3e5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}