VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank

TL;DR

This paper introduces VisualQuality-R1, a reinforcement learning-based no-reference image quality assessment model that leverages visual reasoning, outperforming existing models and providing human-aligned quality descriptions across multiple datasets.

Contribution

We propose VisualQuality-R1, a novel reasoning-induced NR-IQA model trained with reinforcement learning to rank, capable of human-aligned quality descriptions and multi-dataset training.

Findings

Outperforms existing NR-IQA models in accuracy.

Generates human-aligned, context-rich quality descriptions.

Supports multi-dataset training without perceptual scale realignment.

Abstract

DeepSeek-R1 has demonstrated remarkable effectiveness in incentivizing reasoning and generalization capabilities of large language models (LLMs) through reinforcement learning. Nevertheless, the potential of reasoning-induced computation has not been thoroughly explored in the context of image quality assessment (IQA), a task depending critically on visual reasoning. In this paper, we introduce VisualQuality-R1, a reasoning-induced no-reference IQA (NR-IQA) model, and we train it with reinforcement learning to rank, a learning algorithm tailored to the intrinsically relative nature of visual quality. Specifically, for a pair of images, we employ group relative policy optimization to generate multiple quality scores for each image. These estimates are used to compute comparative probabilities of one image having higher quality than the other under the Thurstone model. Rewards for each quality estimate are defined using continuous fidelity measures rather than discretized binary labels. Extensive experiments show that the proposed VisualQuality-R1 consistently outperforms discriminative deep learning-based NR-IQA models as well as a recent reasoning-induced quality regression method. Moreover, VisualQuality-R1 is capable of generating contextually rich, human-aligned quality descriptions, and supports multi-dataset training without requiring perceptual scale realignment. These features make VisualQuality-R1 especially well-suited for reliably measuring progress in a wide range of image processing tasks like super-resolution and image generation.