Lune

CVPR2026Top-tier venue

Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling

Long Tang, Huiyu Duan, Guoquan Zheng, Jianbo Zhang, Jie Hao, Liang Yuan

Abstract

Blind image quality assessment (BIQA) plays a crucial role in evaluating and optimizing visual experience. Most existing BIQA approaches fuse shallow and deep features extracted from backbone networks, while overlooking the unequal contributions to quality prediction. Moreover, while various vision encoder backbones are widely adopted in BIQA, the effective quality decoding architectures remain underexplored. To address these limitations, this paper investigates the contributions of shallow and deep features to BIQA, and proposes a effective quality feature decoding framework via GCN-enhanced layerinteraction and MoE-based feature decoupling, termed (Life-IQA). Specifically, the GCN-enhanced layer interaction module utilizes the GCN-enhanced deepest-layer features as query and the penultimate-layer features as key, value, then performs cross-attention to achieve feature interaction. Moreover, a MoE-based feature decoupling module is proposed to decouple fused representations though different experts specialized for specific distortion types or quality dimensions. Extensive experiments demonstrate that Life-IQA shows more favorable balance between accuracy and cost than a vanilla Transformer decoder and achieves state-of-the-art performance on multiple BIQA benchmarks.The code is available at: Life-IQA.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale cites GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
  • Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
  • Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on19

  1. Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 citations
  2. An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
  3. Searching for MobileNetV3Andrew Howard, Ruoming Pang, Hartwig Adam, Quoc V. Le et al.ICCV 2019 · 9,163 citations
  4. Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without ConvolutionsWenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan et al.ICCV 2021 · 4,909 citations
  5. GShard: Scaling Giant Models with Conditional Computation and Automatic ShardingDmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen et al.ICLR 2021 · 1,954 citations

Related papers

  1. Data-Efficient Image Quality Assessment with Attention-Panel DecoderGuanyi Qin, Runze Hu, Yutao Liu, Xiawu Zheng et al.AAAI 2023 · 113 citations
  2. DR.Experts: Differential Refinement of Distortion-Aware Experts for Blind Image Quality AssessmentBohan Fu, Guanyi Qin, Fazhan Zhang, Zihao Huang et al.AAAI 2026 · 1 citation
  3. Re-IQA: Unsupervised Learning for Image Quality Assessment in the WildAvinab Saha, Sandeep Mishra, Alan C. BovikCVPR 2023
  4. Feature Denoising Diffusion Model for Blind Image Quality AssessmentXudong Li, Yan Zhang, Yunhang Shen, Ke Li et al.AAAI 2025
  5. Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper NetworkShaolin Su, Qingsen Yan, Yu Zhu, Cheng Zhang et al.CVPR 2020
Dusk over the sea between two cliffs drawn in fine vertical lines