# Deep Shape-Texture Statistics for Completely Blind Image Quality Evaluation

arXiv: https://arxiv.org/abs/2401.08107 · HTML: https://mlsanity.com/paper/2401.08107/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 101 references that are in the map.
- First posted on arXiv 16 Jan 2024.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality](https://mlsanity.com/paper/1912.10088/) (2019)
- [Massive Online Crowdsourced Study of Subjective and Objective Picture Quality](https://mlsanity.com/paper/1511.02919/) (2015)
- [PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration](https://mlsanity.com/paper/2007.12142/) (2020)
- [Style Transfer by Relaxed Optimal Transport and Self-Similarity](https://mlsanity.com/paper/1904.12785/) (2019)
- [RankIQA: Learning from Rankings for No-reference Image Quality Assessment](https://mlsanity.com/paper/1707.08347/) (2017)
- [AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2306.04717/) (2023)
- [Shape-Texture Debiased Neural Network Training](https://mlsanity.com/paper/2010.05981/) (2020)
- [dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs](https://mlsanity.com/paper/1904.06505/) (2019)
- [Informative Dropout for Robust Representation Learning: A Shape-bias Perspective](https://mlsanity.com/paper/2008.04254/) (2020)
- [Shape or Texture: Understanding Discriminative Features in CNNs](https://mlsanity.com/paper/2101.11604/) (2021)
- [GIQA: Generated Image Quality Assessment](https://mlsanity.com/paper/2003.08932/) (2020)
- [On the Texture Bias for Few-Shot CNN Segmentation](https://mlsanity.com/paper/2003.04052/) (2020)
- [Does enhanced shape bias improve neural network robustness to common corruptions?](https://mlsanity.com/paper/2104.09789/) (2021)
- [Locally Adaptive Structure and Texture Similarity for Image Quality Assessment](https://mlsanity.com/paper/2110.08521/) (2021)
- [Eigen-Distortions of Hierarchical Representations](https://mlsanity.com/paper/1710.02266/) (2017)

## Built on by (most cited first, 5 of 5)

- [DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor](https://mlsanity.com/paper/2406.08377/) (2024)
- [Puzzle Similarity: A Perceptually-guided Cross-Reference Metric for Artifact Detection in 3D Scene Reconstructions](https://mlsanity.com/paper/2411.17489/) (2024)
- [Decoupling Perception and Calibration: Label-Efficient Image Quality Assessment Framework](https://mlsanity.com/paper/2601.20689/) (2026)
- [ELIQ: A Label-Free Framework for Quality Assessment of Evolving AI-Generated Images](https://mlsanity.com/paper/2602.03558/) (2026)
- [Local SVD-Entropy Maps as a Complementary Structural Representation for Full-Reference and No-Reference Image Quality Assessment](https://mlsanity.com/paper/2609.27959/) (2026)

## Abstract (arXiv)

Opinion-Unaware Blind Image Quality Assessment (OU-BIQA) models aim to predict image quality without training on reference images and subjective quality scores. Thereinto, image statistical comparison is a classic paradigm, while the performance is limited by the representation ability of visual descriptors. Deep features as visual descriptors have advanced IQA in recent research, but they are discovered to be highly texture-biased and lack of shape-bias. On this basis, we find out that image shape and texture cues respond differently towards distortions, and the absence of either one results in an incomplete image representation. Therefore, to formulate a well-round statistical description for images, we utilize the shapebiased and texture-biased deep features produced by Deep Neural Networks (DNNs) simultaneously. More specifically, we design a Shape-Texture Adaptive Fusion (STAF) module to merge shape and texture information, based on which we formulate qualityrelevant image statistics. The perceptual quality is quantified by the variant Mahalanobis Distance between the inner and outer Shape-Texture Statistics (DSTS), wherein the inner and outer statistics respectively describe the quality fingerprints of the distorted image and natural images. The proposed DSTS delicately utilizes shape-texture statistical relations between different data scales in the deep domain, and achieves state-of-the-art (SOTA) quality prediction performance on images with artificial and authentic distortions.