QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restoration

• URL: http://arxiv.org/abs/2603.08030v1
• Date: Mon, 09 Mar 2026 07:06:12 GMT
• Title: QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restoration
• Abstract summary: QualiTeacher is a novel framework that transforms pseudo-label quality from a noisy liability into a conditional supervisory signal.<n>It teaches the student network to learn a quality-graded restoration manifold, enabling it to understand what constitutes different quality levels.<n> Experiments on standard RWIR benchmarks demonstrate that QualiTeacher can serve as a plug-and-play strategy to improve the quality of the existing pseudo-labeling framework.
• Score: 23.7406836456618
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world image restoration (RWIR) is a highly challenging task due to the absence of clean ground-truth images. Many recent methods resort to pseudo-label (PL) supervision, often within a Mean-Teacher (MT) framework. However, these methods face a critical paradox: unconditionally trusting the often imperfect, low-quality PLs forces the student model to learn undesirable artifacts, while discarding them severely limits data diversity and impairs model generalization. In this paper, we propose QualiTeacher, a novel framework that transforms pseudo-label quality from a noisy liability into a conditional supervisory signal. Instead of filtering, QualiTeacher explicitly conditions the student model on the quality of the PLs, estimated by an ensemble of complementary non-reference image quality assessment (NR-IQA) models spanning low-level distortion and semantic-level assessment. This strategy teaches the student network to learn a quality-graded restoration manifold, enabling it to understand what constitutes different quality levels. Consequently, it can not only avoid mimicking artifacts from low-quality labels but also extrapolate to generate results of higher quality than the teacher itself. To ensure the robustness and accuracy of this quality-driven learning, we further enhance the process with a multi-augmentation scheme to diversify the PL quality spectrum, a score-based preference optimization strategy inspired by Direct Preference Optimization (DPO) to enforce a monotonically ordered quality separation, and a cropped consistency loss to prevent adversarial over-optimization (reward hacking) of the IQA models. Experiments on standard RWIR benchmarks demonstrate that QualiTeacher can serve as a plug-and-play strategy to improve the quality of the existing pseudo-labeling framework, establishing a new paradigm for learning from imperfect supervision. Code will be released.

Related papers

• Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement [58.15004031934379]
  We propose Q-DeepSight, a think-with-image framework that emulates this human-like process.<n>Q-DeepSight achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content.<n>We demonstrate its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement.
  arXiv  Detail & Related papers  (2026-04-18T06:10:57Z)
• Radiology Report Generation for Low-Quality X-Ray Images [47.455316078409]
  Vision-Language Models (VLMs) have significantly advanced automated Radiology Report Generation (RRG)<n>Existing methods implicitly assume high-quality inputs, overlooking the noise and artifacts prevalent in real-world clinical environments.<n>We propose a robust report generation framework explicitly designed for image quality variations.
  arXiv  Detail & Related papers  (2026-04-11T12:42:37Z)
• Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration [21.358966811756645]
  Real-world image restoration aims to restore high-quality (HQ) images from degraded low-quality (LQ) inputs captured under uncontrolled conditions.<n>Existing methods typically depend on ground-truth (GT) supervision, assuming that GT provides perfect reference quality.<n>We propose an Image Quality Prior (IQP)-extracted from pre-trained No-Reference Image Quality Assessment (NR-IQA) models-to guide the restoration process toward perceptually optimal outputs explicitly.
  arXiv  Detail & Related papers  (2026-03-31T14:13:10Z)
• SHAMISA: SHAped Modeling of Implicit Structural Associations for Self-supervised No-Reference Image Quality Assessment [6.175621390241037]
  No-Reference Image Quality Assessment (NR-IQA) aims to estimate perceptual quality without access to a reference image of pristine quality.<n>We propose SHAMISA, a non-contrastive self-supervised framework that learns from unlabeled distorted images by leveraging explicitly structured supervision.
  arXiv  Detail & Related papers  (2026-03-14T00:37:26Z)
• ELIQ: A Label-Free Framework for Quality Assessment of Evolving AI-Generated Images [76.5101823186747]
  We present ELIQ, a Label-free Framework for Quality Assessment of Evolving AI-generated Images.<n>Specifically, ELIQ focuses on visual quality and prompt-image alignment.<n>It automatically constructs positive and aspect-specific negative pairs to cover both conventional distortions and AIGC-specific distortion modes.
  arXiv  Detail & Related papers  (2026-02-03T14:04:51Z)
• OmniQuality-R: Advancing Reward Models Through All-Encompassing Quality Assessment [55.59322229889159]
  We propose OmniQuality-R, a unified reward modeling framework that transforms multi-task quality reasoning into continuous and interpretable reward signals.<n>We use a reasoning-enhanced reward modeling dataset to form a reliable chain-of-thought dataset for supervised fine-tuning.<n>We evaluate OmniQuality-R on three key IQA tasks: aesthetic quality assessment, technical quality evaluation, and text-image alignment.
  arXiv  Detail & Related papers  (2025-10-12T13:46:28Z)
• FROQ: Observing Face Recognition Models for Efficient Quality Assessment [5.154970335677459]
  Face Recognition (FR) plays a crucial role in many critical (high-stakes) applications.<n>Most state-of-the-art FIQA techniques rely on extensive supervised training to achieve accurate quality estimation.<n>In this paper, we introduce FROQ, a semi-supervised, training-free approach to estimate face-image quality.
  arXiv  Detail & Related papers  (2025-09-22T12:29:44Z)
• HiRQA: Hierarchical Ranking and Quality Alignment for Opinion-Unaware Image Quality Assessment [10.761579471650771]
  HiRQA is a self-supervised, opinion-unaware framework that offers a hierarchical, quality-aware embedding through a combination of ranking and contrastive learning.<n>For real-time deployment, we introduce textbfHiRQA-S, a lightweight variant with an inference time of only 3.5 ms per image.
  arXiv  Detail & Related papers  (2025-08-20T23:48:21Z)
• IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond [56.99331967165238]
  Blind Face Restoration (BFR) addresses the challenge of reconstructing degraded low-quality (LQ) facial images into high-quality (HQ) outputs.<n>We propose a novel framework that incorporates an Image Quality Prior (IQP) derived from No-Reference Image Quality Assessment (NR-IQA) models.<n>Our method outperforms state-of-the-art techniques across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-03-12T11:39:51Z)
• DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild [73.6767681305851]
  Blind image quality assessment (IQA) in the wild presents significant challenges.<n>Given the difficulty in collecting large-scale training data, leveraging limited data to develop a model with strong generalization remains an open problem.<n>Motivated by the robust image perception capabilities of pre-trained text-to-image (T2I) diffusion models, we propose a novel IQA method, diffusion priors-based IQA.
  arXiv  Detail & Related papers  (2024-05-30T12:32:35Z)
• Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild [38.197794061203055]
  We propose a Mixture of Experts approach to train two separate encoders to learn high-level content and low-level image quality features in an unsupervised setting. We deploy the complementary low and high-level image representations obtained from the Re-IQA framework to train a linear regression model. Our method achieves state-of-the-art performance on multiple large-scale image quality assessment databases.
  arXiv  Detail & Related papers  (2023-04-02T05:06:51Z)
• Image Quality Assessment using Contrastive Learning [50.265638572116984]
  We train a deep Convolutional Neural Network (CNN) using a contrastive pairwise objective to solve the auxiliary problem. We show through extensive experiments that CONTRIQUE achieves competitive performance when compared to state-of-the-art NR image quality models. Our results suggest that powerful quality representations with perceptual relevance can be obtained without requiring large labeled subjective image quality datasets.
  arXiv  Detail & Related papers  (2021-10-25T21:01:00Z)

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.