{"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/topiq-a-top-down-approach-from-semantics-to","title":"TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment","arxiv_id":"2308.03060","date":"2023-08-06","proceeding":null,"authors":["Chaofeng Chen","Jiadi Mo","Jingwen Hou","HaoNing Wu","Liang Liao","Wenxiu Sun","Qiong Yan","Weisi Lin"],"abstract":"Image Quality Assessment (IQA) is a fundamental task in computer vision that has witnessed remarkable progress with deep neural networks. Inspired by the characteristics of the human visual system, existing methods typically use a combination of global and local representations (\\ie, multi-scale features) to achieve superior performance. However, most of them adopt simple linear fusion of multi-scale features, and neglect their possibly complex relationship and interaction. In contrast, humans typically first form a global impression to locate important regions and then focus on local details in those regions. We therefore propose a top-down approach that uses high-level semantics to guide the IQA network to focus on semantically important local distortion regions, named as \\emph{TOPIQ}. Our approach to IQA involves the design of a heuristic coarse-to-fine network (CFANet) that leverages multi-scale features and progressively propagates multi-level semantic information to low-level representations in a top-down manner. A key component of our approach is the proposed cross-scale attention mechanism, which calculates attention maps for lower level features guided by higher level features. This mechanism emphasizes active semantic regions for low-level distortions, thereby improving performance. CFANet can be used for both Full-Reference (FR) and No-Reference (NR) IQA. We use ResNet50 as its backbone and demonstrate that CFANet achieves better or competitive performance on most public FR and NR benchmarks compared with state-of-the-art methods based on vision transformers, while being much more efficient (with only ${\\sim}13\\%$ FLOPS of the current best FR method). Codes are released at \\url{https://github.com/chaofengc/IQA-PyTorch}.","url_abs":"https://arxiv.org/abs/2308.03060v1","url_pdf":"https://arxiv.org/pdf/2308.03060v1.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":"topiq-a-top-down-approach-from-semantics-to","repo_url":"https://github.com/chaofengc/iqa-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"local-distortion","task_name":"Local Distortion"},{"task_slug":"no-reference-image-quality-assessment","task_name":"No-Reference Image Quality Assessment"},{"task_slug":"video-quality-assessment","task_name":"Video Quality Assessment"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"TOPIQ\ntrained on SPAQ (NR)","rank_in_archive_order":11,"of":60,"metrics":{"KLCC":"0.53140","PLCC":"0.60905","SROCC":"0.64923","Type":"NR"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"TOPIQ","rank_in_archive_order":14,"of":60,"metrics":{"KLCC":"0.50670","PLCC":"0.57674","SROCC":"0.62715","Type":"NR"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"TOPIQ FACE","rank_in_archive_order":21,"of":60,"metrics":{"KLCC":"0.48428","PLCC":"0.58949","SROCC":"0.59564","Type":"NR"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"TOPIQ","rank_in_archive_order":23,"of":60,"metrics":{"KLCC":"0.46217","PLCC":"0.57955","SROCC":"0.57341","Type":"FR"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"TOPIQ\ntrained on PIPAL","rank_in_archive_order":27,"of":60,"metrics":{"KLCC":"0.42811","PLCC":"0.57564","SROCC":"0.55568","Type":"FR"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"TOPIQ (IAA)","rank_in_archive_order":35,"of":60,"metrics":{"KLCC":"0.40663","PLCC":"0.51061","SROCC":"0.51687","Type":"NR"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"TOPIQ + Res50 (IAA)","rank_in_archive_order":42,"of":60,"metrics":{"KLCC":"0.28473","PLCC":"0.34000","SROCC":"0.36204","Type":"NR"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"TOPIQ\ntrained on FLIVE","rank_in_archive_order":45,"of":60,"metrics":{"KLCC":"0.26774","PLCC":"0.33940","SROCC":"0.34092","Type":"NR"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.03060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03060"}},"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/chaofengc/iqa-pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":3,"unverified":7},"by_repo_kind":{"official":{"samples":10,"ran":3,"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":10,"samples":[{"code_sha256_prefix":"03c4d04768b427ed","entry":"norm_loss_with_normalization","repo":"chaofengc/iqa-pytorch","repo_kind":"official","path":"pyiqa/losses/iqa_losses.py","file_url":"https://github.com/chaofengc/iqa-pytorch/blob/HEAD/pyiqa/losses/iqa_losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"03c4d04768b427ed"}},{"code_sha256_prefix":"085c0ae1d875a3e2","entry":"plcc_loss","repo":"chaofengc/iqa-pytorch","repo_kind":"official","path":"pyiqa/losses/iqa_losses.py","file_url":"https://github.com/chaofengc/iqa-pytorch/blob/HEAD/pyiqa/losses/iqa_losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"085c0ae1d875a3e2"}},{"code_sha256_prefix":"06964fd66b132112","entry":"str_to_bool","repo":"chaofengc/iqa-pytorch","repo_kind":"official","path":"benchmark_results.py","file_url":"https://github.com/chaofengc/iqa-pytorch/blob/HEAD/benchmark_results.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"06964fd66b132112"}},{"code_sha256_prefix":"e15e0f88defc7c70","entry":"build_model","repo":"chaofengc/iqa-pytorch","repo_kind":"official","path":"pyiqa/archs/afineclip_model.py","file_url":"https://github.com/chaofengc/iqa-pytorch/blob/HEAD/pyiqa/archs/afineclip_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e15e0f88defc7c70"}},{"code_sha256_prefix":"f459f1b3bcda12f6","entry":"build_model","repo":"chaofengc/iqa-pytorch","repo_kind":"official","path":"pyiqa/archs/clip_model.py","file_url":"https://github.com/chaofengc/iqa-pytorch/blob/HEAD/pyiqa/archs/clip_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f459f1b3bcda12f6"}},{"code_sha256_prefix":"66c27cd25f8c24da","entry":"expand2square","repo":"chaofengc/iqa-pytorch","repo_kind":"official","path":"pyiqa/archs/compare2score_arch.py","file_url":"https://github.com/chaofengc/iqa-pytorch/blob/HEAD/pyiqa/archs/compare2score_arch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"66c27cd25f8c24da"}},{"code_sha256_prefix":"024e0b35d03e4520","entry":"flatten_list","repo":"chaofengc/iqa-pytorch","repo_kind":"official","path":"benchmark_results.py","file_url":"https://github.com/chaofengc/iqa-pytorch/blob/HEAD/benchmark_results.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":"024e0b35d03e4520"}},{"code_sha256_prefix":"2404f7ff4c470f2c","entry":"get_dataset_info","repo":"chaofengc/iqa-pytorch","repo_kind":"official","path":"pyiqa/api_helpers.py","file_url":"https://github.com/chaofengc/iqa-pytorch/blob/HEAD/pyiqa/api_helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2404f7ff4c470f2c"}},{"code_sha256_prefix":"b6761b4b4e8d8987","entry":"load","repo":"chaofengc/iqa-pytorch","repo_kind":"official","path":"pyiqa/archs/afineclip_model.py","file_url":"https://github.com/chaofengc/iqa-pytorch/blob/HEAD/pyiqa/archs/afineclip_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b6761b4b4e8d8987"}},{"code_sha256_prefix":"832a38a42cafb12b","entry":"load","repo":"chaofengc/iqa-pytorch","repo_kind":"official","path":"pyiqa/archs/clip_model.py","file_url":"https://github.com/chaofengc/iqa-pytorch/blob/HEAD/pyiqa/archs/clip_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"832a38a42cafb12b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}