{"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/training-generative-image-super-resolution","title":"Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts","arxiv_id":"2402.19215","date":"2024-02-29","proceeding":"CVPR 2024 1","authors":["Cansu Korkmaz","A. Murat Tekalp","Zafer Dogan"],"abstract":"Super-resolution (SR) is an ill-posed inverse problem, where the size of the set of feasible solutions that are consistent with a given low-resolution image is very large. Many algorithms have been proposed to find a \"good\" solution among the feasible solutions that strike a balance between fidelity and perceptual quality. Unfortunately, all known methods generate artifacts and hallucinations while trying to reconstruct high-frequency (HF) image details. A fundamental question is: Can a model learn to distinguish genuine image details from artifacts? Although some recent works focused on the differentiation of details and artifacts, this is a very challenging problem and a satisfactory solution is yet to be found. This paper shows that the characterization of genuine HF details versus artifacts can be better learned by training GAN-based SR models using wavelet-domain loss functions compared to RGB-domain or Fourier-space losses. Although wavelet-domain losses have been used in the literature before, they have not been used in the context of the SR task. More specifically, we train the discriminator only on the HF wavelet sub-bands instead of on RGB images and the generator is trained by a fidelity loss over wavelet subbands to make it sensitive to the scale and orientation of structures. Extensive experimental results demonstrate that our model achieves better perception-distortion trade-off according to multiple objective measures and visual evaluations.","url_abs":"https://arxiv.org/abs/2402.19215v1","url_pdf":"https://arxiv.org/pdf/2402.19215v1.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":"training-generative-image-super-resolution","repo_url":"https://github.com/mandalinadagi/wgsr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.19215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19215"}},"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/mandalinadagi/wgsr","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":4,"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"15d829a065897df0","entry":"act","repo":"mandalinadagi/wgsr","repo_kind":"official","path":"test_image/block.py","file_url":"https://github.com/mandalinadagi/wgsr/blob/HEAD/test_image/block.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"15d829a065897df0"}},{"code_sha256_prefix":"c04a23de0531da4a","entry":"make_layer","repo":"mandalinadagi/wgsr","repo_kind":"official","path":"codes/models/RRDBNet_arch.py","file_url":"https://github.com/mandalinadagi/wgsr/blob/HEAD/codes/models/RRDBNet_arch.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c04a23de0531da4a"}},{"code_sha256_prefix":"5e656210252d9f33","entry":"mypad","repo":"mandalinadagi/wgsr","repo_kind":"official","path":"codes/models/SWT.py","file_url":"https://github.com/mandalinadagi/wgsr/blob/HEAD/codes/models/SWT.py","link_basis":"harvester_set","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":"5e656210252d9f33"}},{"code_sha256_prefix":"b6a238bb90c0069b","entry":"norm","repo":"mandalinadagi/wgsr","repo_kind":"official","path":"test_image/block.py","file_url":"https://github.com/mandalinadagi/wgsr/blob/HEAD/test_image/block.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b6a238bb90c0069b"}},{"code_sha256_prefix":"4a56ce1917d87f9b","entry":"pad","repo":"mandalinadagi/wgsr","repo_kind":"official","path":"test_image/block.py","file_url":"https://github.com/mandalinadagi/wgsr/blob/HEAD/test_image/block.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4a56ce1917d87f9b"}},{"code_sha256_prefix":"a1070467a2c29db6","entry":"prep_filt_afb2d","repo":"mandalinadagi/wgsr","repo_kind":"official","path":"codes/models/SWT.py","file_url":"https://github.com/mandalinadagi/wgsr/blob/HEAD/codes/models/SWT.py","link_basis":"harvester_set","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":"a1070467a2c29db6"}},{"code_sha256_prefix":"c18931526ac3006c","entry":"reflect","repo":"mandalinadagi/wgsr","repo_kind":"official","path":"codes/models/SWT.py","file_url":"https://github.com/mandalinadagi/wgsr/blob/HEAD/codes/models/SWT.py","link_basis":"harvester_set","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":"c18931526ac3006c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}