# Image Quality Assessment: Enhancing Perceptual Exploration and Interpretation with Collaborative Feature Refinement and Hausdorff distance

arXiv: https://arxiv.org/abs/2412.15847 · HTML: https://mlsanity.com/paper/2412.15847/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 49 references that are in the map.
- First posted on arXiv 20 Dec 2024.

## Builds on (most cited first, 19 of 19)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment](https://mlsanity.com/paper/2308.03060/) (2023)
- [PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration](https://mlsanity.com/paper/2007.12142/) (2020)
- [Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion](https://mlsanity.com/paper/2111.12702/) (2021)
- [HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms](https://mlsanity.com/paper/2011.11731/) (2020)
- [Masked Image Training for Generalizable Deep Image Denoising](https://mlsanity.com/paper/2303.13132/) (2023)
- [Perceptual Image Quality Assessment with Transformers](https://mlsanity.com/paper/2104.14730/) (2021)
- [Locally Adaptive Structure and Texture Similarity for Image Quality Assessment](https://mlsanity.com/paper/2110.08521/) (2021)
- [DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space](https://mlsanity.com/paper/2208.03323/) (2022)
- [Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning](https://mlsanity.com/paper/2403.02601/) (2024)
- [Opinion-Unaware Blind Image Quality Assessment using Multi-Scale Deep Feature Statistics](https://mlsanity.com/paper/2405.18790/) (2024)
- [Boosting Flow-based Generative Super-Resolution Models via Learned Prior](https://mlsanity.com/paper/2403.10988/) (2024)
- [Full Reference Screen Content Image Quality Assessment by Fusing Multi-level Structure Similarity](https://mlsanity.com/paper/2008.05396/) (2020)
- [Degraded Reference Image Quality Assessment](https://mlsanity.com/paper/2110.14899/) (2021)
- [DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor](https://mlsanity.com/paper/2406.08377/) (2024)
- [Full-Reference Calibration-Free Image Quality Assessment](https://mlsanity.com/paper/2205.12129/) (2022)
- [Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain](https://mlsanity.com/paper/2402.17200/) (2024)

## Abstract (arXiv)

Current full-reference image quality assessment (FR-IQA) methods often fuse features from reference and distorted images, overlooking that color and luminance distortions occur mainly at low frequencies, whereas edge and texture distortions occur at high frequencies. This work introduces a pioneering training-free FR-IQA method that accurately predicts image quality in alignment with the human visual system (HVS) by leveraging a novel perceptual degradation modelling approach to address this limitation. First, a collaborative feature refinement module employs a carefully designed wavelet transform to extract perceptually relevant features, capturing multiscale perceptual information and mimicking how the HVS analyses visual information at various scales and orientations in the spatial and frequency domains. Second, a Hausdorff distance-based distribution similarity measurement module robustly assesses the discrepancy between the feature distributions of the reference and distorted images, effectively handling outliers and variations while mimicking the ability of HVS to perceive and tolerate certain levels of distortion. The proposed method accurately captures perceptual quality differences without requiring training data or subjective quality scores. Extensive experiments on multiple benchmark datasets demonstrate superior performance compared with existing state-of-the-art approaches, highlighting its ability to correlate strongly with the HVS.footnoteThe code is available at urlhttps://anonymous.4open.science/r/CVPR2025-F339.