NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)

TL;DR

This paper overviews the NTIRE 2026 challenge focusing on using multimodal large language models to evaluate high-quality images, emphasizing comparison and interpretative reasoning, with a new benchmark and dataset.

Contribution

It introduces a novel benchmark and challenge for professional image quality assessment using MLLMs, emphasizing interpretative reasoning and comparison capabilities.

Findings

Top methods significantly advanced the state of the art in professional IQA.

Nearly 200 teams registered, with over 2,500 submissions.

The challenge dataset and homepage are publicly available.

Abstract

In this paper, we present an overview of the NTIRE 2026 challenge on the 3rd Restore Any Image Model in the Wild, specifically focusing on Track 1: Professional Image Quality Assessment. Conventional Image Quality Assessment (IQA) typically relies on scalar scores. By compressing complex visual characteristics into a single number, these methods fundamentally struggle to distinguish subtle differences among uniformly high-quality images. Furthermore, they fail to articulate why one image is superior, lacking the reasoning capabilities required to provide guidance for vision tasks. To bridge this gap, recent advancements in Multimodal Large Language Models (MLLMs) offer a promising paradigm. Inspired by this potential, our challenge establishes a novel benchmark exploring the ability of MLLMs to mimic human expert cognition in evaluating high-quality image pairs. Participants were tasked with overcoming critical bottlenecks in professional scenarios, centering on two primary objectives: (1) Comparative Quality Selection: reliably identifying the visually superior image within a high-quality pair; and (2) Interpretative Reasoning: generating grounded, expert-level explanations that detail the rationale behind the selection. In total, the challenge attracted nearly 200 registrations and over 2,500 submissions. The top-performing methods significantly advanced the state of the art in professional IQA. The challenge dataset is available at https://github.com/narthchin/RAIM-PIQA, and the official homepage is accessible at https://www.codabench.org/competitions/12789/.