Papers › MUSIQ: Multi-scale Image Quality Transformer

MUSIQ: Multi-scale Image Quality Transformer

12 Aug 2021ICCV 2021 10arXiv:2108.05997archive 2025-07-28

Junjie Ke, Qifei Wang, Yilin Wang, Peyman Milanfar, Feng Yang

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2108.05997")

Code

Syntology Ran 5 of 6 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · our draft was wrong; 4 ran with no contract checked.

By repository: community (archive-listed): 6 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

anse3832/MUSIQ mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested; 5 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
4ran
1unverified

Licence: 6 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from anse3832/MUSIQ. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

EncoderLayer anse3832/MUSIQ/model/model_main.py community (archive-listed) ran no licence file found · pointer only · d2b4c70296ff9591 · report
MultiHeadAttention anse3832/MUSIQ/model/model_main.py community (archive-listed) ran no licence file found · pointer only · 40eb87901e9f32af · report
PoswiseFeedForwardNet anse3832/MUSIQ/model/model_main.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 6dd1b5927cf9f3a6 · report
ScaledDotProductAttention anse3832/MUSIQ/model/model_main.py community (archive-listed) ran no licence file found · pointer only · 84dca3bde2cc13a1 · report
get_attn_pad_mask anse3832/MUSIQ/model/model_main.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · 1d46b5657fff1e67 · report
Encoder anse3832/MUSIQ/model/model_main.py community (archive-listed) unverified no licence file found · pointer only · c0896be4ab87d978 · report

Tasks

Image Quality AssessmentVideo Quality Assessment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Quality Assessment MSU NR VQA Database MUSIQ KLCC 0.7433 #3 of 10 Archive leaderboard report
Image Quality Assessment MSU NR VQA Database MUSIQ PLCC 0.9068 #3 of 10 Archive leaderboard report
Image Quality Assessment MSU NR VQA Database MUSIQ SRCC 0.9004 #3 of 10 Archive leaderboard report
Video Quality Assessment MSU NR VQA Database MUSIQ KLCC 0.7433 #7 of 21 Archive leaderboard report
Video Quality Assessment MSU NR VQA Database MUSIQ PLCC 0.9068 #7 of 21 Archive leaderboard report
Video Quality Assessment MSU NR VQA Database MUSIQ SRCC 0.9004 #7 of 21 Archive leaderboard report
Video Quality Assessment MSU NR VQA Database MUSIQ Type NR #7 of 21 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on PaQ-2-PiQ KLCC 0.55312 #6 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on PaQ-2-PiQ PLCC 0.66531 #6 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on PaQ-2-PiQ SROCC 0.67746 #6 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on PaQ-2-PiQ Type NR #6 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on SPAQ KLCC 0.52673 #10 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on SPAQ PLCC 0.60216 #10 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on SPAQ SROCC 0.64927 #10 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on SPAQ Type NR #10 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on KONIQ KLCC 0.51897 #12 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on KONIQ PLCC 0.59151 #12 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on KONIQ SROCC 0.64589 #12 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on KONIQ Type NR #12 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on AVA KLCC 0.44669 #26 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on AVA PLCC 0.52404 #26 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on AVA SROCC 0.56152 #26 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset MUSIQ trained on AVA Type NR #26 of 60 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: MUSIQ

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMUSIQMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections