MSPT: A Lightweight Face Image Quality Assessment Method with Multi-stage Progressive Training

• URL: http://arxiv.org/abs/2508.07590v1
• Date: Mon, 11 Aug 2025 03:37:09 GMT
• Title: MSPT: A Lightweight Face Image Quality Assessment Method with Multi-stage Progressive Training
• Abstract summary: We propose a lightweight face quality assessment network with Multi-Stage Progressive Training (MSPT)<n>Our network employs a three-stage progressive training strategy that gradually introduces more diverse data samples.<n>MSPT achieved the second highest score on the VQualA 2025 face image quality assessment benchmark dataset.
• Score: 2.4399096457147356
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Accurately assessing the perceptual quality of face images is crucial, especially with the rapid progress in face restoration and generation. Traditional quality assessment methods often struggle with the unique characteristics of face images, limiting their generalizability. While learning-based approaches demonstrate superior performance due to their strong fitting capabilities, their high complexity typically incurs significant computational and storage costs, hindering practical deployment. To address this, we propose a lightweight face quality assessment network with Multi-Stage Progressive Training (MSPT). Our network employs a three-stage progressive training strategy that gradually introduces more diverse data samples and increases input image resolution. This novel approach enables lightweight networks to achieve high performance by effectively learning complex quality features while significantly mitigating catastrophic forgetting. Our MSPT achieved the second highest score on the VQualA 2025 face image quality assessment benchmark dataset, demonstrating that MSPT achieves comparable or better performance than state-of-the-art methods while maintaining efficient inference.

Related papers

• Patch Knowledge Transfer for Efficient AI-Generated Image Quality Assessment [0.0]
  Current mainstream approaches exhibit two key limitations.<n>We propose Patch Knowledge Transfer (PKT), a knowledge distillation-based optimization framework.<n>We show that PKT enables the student model to maintain performance comparable to the teacher while reducing computational costs by 67.7%.
  arXiv  Detail & Related papers  (2026-07-06T20:02:25Z)
• ATTN-FIQA: Interpretable Attention-based Face Image Quality Assessment with Vision Transformers [19.095360516976847]
  Face Image Quality Assessment (FIQA) aims to assess the recognition utility of face samples and is essential for reliable face recognition (FR) systems.<n>Recent studies highlighted that these architectures inherently function as saliency learners with attention patterns naturally encoding spatial importance.<n>This work proposes ATTN-FIQA, a novel training-free approach that investigates whether pre-softmax attention scores from pre-trained Vision Transformer-based face recognition models can serve as quality indicators.
  arXiv  Detail & Related papers  (2026-04-21T12:46:16Z)
• Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos [99.42805906884499]
  We first introduce a Real-world Low-Quality Face Video benchmark (RFV-LQ) to evaluate leading image-based face restoration algorithms. We then conduct a thorough systematical analysis of the benefits and challenges associated with extending blind face image restoration algorithms to degraded face videos. Our analysis identifies several key issues, primarily categorized into two aspects: significant jitters in facial components and noise-shape flickering between frames.
  arXiv  Detail & Related papers  (2024-10-15T17:53:25Z)
• Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model [55.46927355649013]
  We introduce a novel Multi-modal Guided Real-World Face Restoration technique.<n>MGFR can mitigate the generation of false facial attributes and identities.<n>We present the Reface-HQ dataset, comprising over 21,000 high-resolution facial images across 4800 identities.
  arXiv  Detail & Related papers  (2024-10-05T13:46:56Z)
• DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer [23.70791030264281]
  Generic Face Image Quality Assessment (GFIQA) evaluates the perceptual quality of facial images. We present a novel transformer-based method for GFIQA, which is aided by two unique mechanisms.
  arXiv  Detail & Related papers  (2024-06-13T23:11:25Z)
• Rank-based No-reference Quality Assessment for Face Swapping [88.53827937914038]
  The metric of measuring the quality in most face swapping methods relies on several distances between the manipulated images and the source image. We present a novel no-reference image quality assessment (NR-IQA) method specifically designed for face swapping.
  arXiv  Detail & Related papers  (2024-06-04T01:36:29Z)
• Boosting Cross-Quality Face Verification using Blind Face Restoration [0.13654846342364302]
  It is crucial for the task of face verification to enhance the perceptual quality of the low quality images. In this paper, we investigate the impact of applying three state-of-the-art blind face restoration techniques on the performance of face verification system.
  arXiv  Detail & Related papers  (2023-08-15T18:05:19Z)
• MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion [8.338999282303755]
  We propose a novel algorithm based on the Swin Transformer. It aggregates information from both local and global features to better predict the quality. It ranks 2nd in the no-reference track of NTIRE 2022 Perceptual Image Quality Assessment Challenge.
  arXiv  Detail & Related papers  (2022-05-20T11:34:35Z)
• Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment [26.792481400792376]
  In many face recognition (FR) scenarios, face images are acquired from a sequence with huge intra-variations. We present an efficient non-reference image quality assessment for FR that directly links image quality assessment (IQA) and FR. Based on the proposed quality measurement, we propose a deep Tiny Face Quality network (tinyFQnet) to learn a quality prediction function from data.
  arXiv  Detail & Related papers  (2021-06-09T07:20:54Z)
• Network Architecture Search for Face Enhancement [82.25775020564654]
  We present a multi-task face restoration network, called Network Architecture Search for Face Enhancement (NASFE) NASFE can enhance poor quality face images containing a single degradation (i.e. noise or blur) or multiple degradations (noise+blur+low-light)
  arXiv  Detail & Related papers  (2021-05-13T19:46:05Z)
• Joint Face Image Restoration and Frontalization for Recognition [79.78729632975744]
  In real-world scenarios, many factors may harm face recognition performance, e.g., large pose, bad illumination,low resolution, blur and noise. Previous efforts usually first restore the low-quality faces to high-quality ones and then perform face recognition. We propose an Multi-Degradation Face Restoration model to restore frontalized high-quality faces from the given low-quality ones.
  arXiv  Detail & Related papers  (2021-05-12T03:52:41Z)
• Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation [92.86123832948809]
  We propose a deep face super-resolution (FSR) method with iterative collaboration between two recurrent networks. In each recurrent step, the recovery branch utilizes the prior knowledge of landmarks to yield higher-quality images. A new attentive fusion module is designed to strengthen the guidance of landmark maps.
  arXiv  Detail & Related papers  (2020-03-29T16:04:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.