{"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/musiq-multi-scale-image-quality-transformer","title":"MUSIQ: Multi-scale Image Quality Transformer","arxiv_id":"2108.05997","date":"2021-08-12","proceeding":"ICCV 2021 10","authors":["Junjie Ke","Qifei Wang","Yilin Wang","Peyman Milanfar","Feng Yang"],"abstract":"Image quality assessment (IQA) is an important research topic for understanding and improving visual experience. The current state-of-the-art IQA methods are based on convolutional neural networks (CNNs). The performance of CNN-based models is often compromised by the fixed shape constraint in batch training. To accommodate this, the input images are usually resized and cropped to a fixed shape, causing image quality degradation. To address this, we design a multi-scale image quality Transformer (MUSIQ) to process native resolution images with varying sizes and aspect ratios. With a multi-scale image representation, our proposed method can capture image quality at different granularities. Furthermore, a novel hash-based 2D spatial embedding and a scale embedding is proposed to support the positional embedding in the multi-scale representation. Experimental results verify that our method can achieve state-of-the-art performance on multiple large scale IQA datasets such as PaQ-2-PiQ, SPAQ and KonIQ-10k.","url_abs":"https://arxiv.org/abs/2108.05997v1","url_pdf":"https://arxiv.org/pdf/2108.05997v1.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":"musiq-multi-scale-image-quality-transformer","repo_url":"https://github.com/google-research/google-research/tree/master/musiq","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"musiq-multi-scale-image-quality-transformer","repo_url":"https://github.com/anse3832/MUSIQ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"video-quality-assessment","task_name":"Video Quality Assessment"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"musiq","method_name":"MUSIQ"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[{"slug":"musiq","name":"MUSIQ","full_name":"MUSIQ"}],"results":[{"leaderboard":"/sota/image-quality-assessment-on-msu-nr-vqa","task":"Image Quality Assessment","dataset":"MSU NR VQA Database","model":"MUSIQ","rank_in_archive_order":3,"of":10,"metrics":{"KLCC":"0.7433","PLCC":"0.9068","SRCC":"0.9004"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-video-quality","task":"Video Quality Assessment","dataset":"MSU NR VQA Database","model":"MUSIQ","rank_in_archive_order":7,"of":21,"metrics":{"KLCC":"0.7433","PLCC":"0.9068","SRCC":"0.9004","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":"MUSIQ\ntrained on PaQ-2-PiQ","rank_in_archive_order":6,"of":60,"metrics":{"KLCC":"0.55312","PLCC":"0.66531","SROCC":"0.67746","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":"MUSIQ\ntrained on SPAQ","rank_in_archive_order":10,"of":60,"metrics":{"KLCC":"0.52673","PLCC":"0.60216","SROCC":"0.64927","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":"MUSIQ\ntrained on KONIQ","rank_in_archive_order":12,"of":60,"metrics":{"KLCC":"0.51897","PLCC":"0.59151","SROCC":"0.64589","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":"MUSIQ\ntrained on AVA","rank_in_archive_order":26,"of":60,"metrics":{"KLCC":"0.44669","PLCC":"0.52404","SROCC":"0.56152","Type":"NR"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.05997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.05997"}},"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/google-research/google-research/tree/master/musiq","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/anse3832/MUSIQ","reach":null}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"listed":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"d2b4c70296ff9591","entry":"EncoderLayer","repo":"anse3832/MUSIQ","repo_kind":"listed","path":"model/model_main.py","file_url":"https://github.com/anse3832/MUSIQ/blob/HEAD/model/model_main.py","link_basis":"first_harvest_node","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":"d2b4c70296ff9591"}},{"code_sha256_prefix":"40eb87901e9f32af","entry":"MultiHeadAttention","repo":"anse3832/MUSIQ","repo_kind":"listed","path":"model/model_main.py","file_url":"https://github.com/anse3832/MUSIQ/blob/HEAD/model/model_main.py","link_basis":"first_harvest_node","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":"40eb87901e9f32af"}},{"code_sha256_prefix":"6dd1b5927cf9f3a6","entry":"PoswiseFeedForwardNet","repo":"anse3832/MUSIQ","repo_kind":"listed","path":"model/model_main.py","file_url":"https://github.com/anse3832/MUSIQ/blob/HEAD/model/model_main.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6dd1b5927cf9f3a6"}},{"code_sha256_prefix":"84dca3bde2cc13a1","entry":"ScaledDotProductAttention","repo":"anse3832/MUSIQ","repo_kind":"listed","path":"model/model_main.py","file_url":"https://github.com/anse3832/MUSIQ/blob/HEAD/model/model_main.py","link_basis":"first_harvest_node","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":"84dca3bde2cc13a1"}},{"code_sha256_prefix":"1d46b5657fff1e67","entry":"get_attn_pad_mask","repo":"anse3832/MUSIQ","repo_kind":"listed","path":"model/model_main.py","file_url":"https://github.com/anse3832/MUSIQ/blob/HEAD/model/model_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d46b5657fff1e67"}},{"code_sha256_prefix":"c0896be4ab87d978","entry":"Encoder","repo":"anse3832/MUSIQ","repo_kind":"listed","path":"model/model_main.py","file_url":"https://github.com/anse3832/MUSIQ/blob/HEAD/model/model_main.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":"c0896be4ab87d978"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}