Methods › Computer Vision › Image Quality Models › MUSIQ

MUSIQ

4 papers tagged archive 2025-07-28

Introduced by Junjie Ke et al. in MUSIQ: Multi-scale Image Quality Transformer

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

MUSIQ, or Multi-scale Image Quality Transformer, is a Transformer-based model for multi-scale image quality assessment. It processes native resolution images with varying sizes and aspect ratios. In MUSIQ, we construct a multi-scale image representation as input, including the native resolution image and its ARP resized variants. Each image is split into fixed-size patches which are embedded by a patch encoding module (blue boxes). To capture 2D structure of the image and handle images of varying aspect ratios, the spatial embedding is encoded by hashing the patch position (i,j) to (tᵢ,tⱼ) within a grid of learnable embeddings (red boxes). Scale Embedding (green boxes) is introduced to capture scale information. The Transformer encoder takes the input tokens and performs multi-head self-attention. To predict the image quality, MUSIQ follows a common strategy in Transformers to add an [CLS] token to the sequence to represent the whole multi-scale input and the corresponding Transformer output is used as the final representation.

Paper Source

Papers archive 2025-07-28

4 shown of 4, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Accelerating Diffusion-based Super-Resolution with Dynamic Time-Spatial Sampling
17 May 2025 · 0 repositories · arXiv:2505.12048
NightHaze: Nighttime Image Dehazing via Self-Prior Learning
12 Mar 2024 · 0 repositories · arXiv:2403.07408
DIFFNAT: Improving Diffusion Image Quality Using Natural Image Statistics
16 Nov 2023 · 0 repositories · arXiv:2311.09753
MUSIQ: Multi-scale Image Quality Transformer
12 Aug 2021 · 2 repositories · arXiv:2108.05997

Syntology ran 5 of 6 samples · 1 unverified · 6 pointer-only (licence)

Tasks archive 2025-07-28

9 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Super-Resolution	2
Denoising	1
Image Dehazing	1
Image Enhancement	1
Image Generation	1
Image Quality Assessment	1
Image Super-Resolution	1
Unconditional Image Generation	1
Video Quality Assessment	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (4 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Image Quality Models Vision Transformers

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