{"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/holisdip-image-super-resolution-via-holistic","title":"HoliSDiP: Image Super-Resolution via Holistic Semantics and Diffusion Prior","arxiv_id":"2411.18662","date":"2024-11-27","proceeding":null,"authors":["Li-Yuan Tsao","Hao-Wei Chen","Hao-Wei Chung","Deqing Sun","Chun-Yi Lee","Kelvin C. K. Chan","Ming-Hsuan Yang"],"abstract":"Text-to-image diffusion models have emerged as powerful priors for real-world image super-resolution (Real-ISR). However, existing methods may produce unintended results due to noisy text prompts and their lack of spatial information. In this paper, we present HoliSDiP, a framework that leverages semantic segmentation to provide both precise textual and spatial guidance for diffusion-based Real-ISR. Our method employs semantic labels as concise text prompts while introducing dense semantic guidance through segmentation masks and our proposed Segmentation-CLIP Map. Extensive experiments demonstrate that HoliSDiP achieves significant improvement in image quality across various Real-ISR scenarios through reduced prompt noise and enhanced spatial control.","url_abs":"https://arxiv.org/abs/2411.18662v1","url_pdf":"https://arxiv.org/pdf/2411.18662v1.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":"holisdip-image-super-resolution-via-holistic","repo_url":"https://github.com/liyuantsao/HoliSDiP","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.18662","atlas_url":"https://app.syntology.ai/?focus=2411.18662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18662"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/liyuantsao/HoliSDiP","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"8d3cd21cd5c3181a","entry":"AttentionBlock","repo":"liyuantsao/HoliSDiP","repo_kind":"official","path":"basicsr/archs/dfdnet_util.py","file_url":"https://github.com/liyuantsao/HoliSDiP/blob/HEAD/basicsr/archs/dfdnet_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8d3cd21cd5c3181a"}},{"code_sha256_prefix":"b7c6741eed724350","entry":"adaptive_instance_normalization","repo":"liyuantsao/HoliSDiP","repo_kind":"official","path":"basicsr/archs/dfdnet_util.py","file_url":"https://github.com/liyuantsao/HoliSDiP/blob/HEAD/basicsr/archs/dfdnet_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b7c6741eed724350"}},{"code_sha256_prefix":"a7e8af4ef5efc131","entry":"calc_mean_std","repo":"liyuantsao/HoliSDiP","repo_kind":"official","path":"basicsr/archs/dfdnet_util.py","file_url":"https://github.com/liyuantsao/HoliSDiP/blob/HEAD/basicsr/archs/dfdnet_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a7e8af4ef5efc131"}},{"code_sha256_prefix":"6e8df2b094350263","entry":"create_normalization","repo":"liyuantsao/HoliSDiP","repo_kind":"official","path":"models/gfm.py","file_url":"https://github.com/liyuantsao/HoliSDiP/blob/HEAD/models/gfm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6e8df2b094350263"}},{"code_sha256_prefix":"da94debb8019ad46","entry":"zero_module","repo":"liyuantsao/HoliSDiP","repo_kind":"official","path":"models/controlnet.py","file_url":"https://github.com/liyuantsao/HoliSDiP/blob/HEAD/models/controlnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"da94debb8019ad46"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}