LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment: Methods and Results

TL;DR

The LoViF 2026 Challenge introduces a new dataset and benchmark for evaluating semantic image quality from a human perspective, promoting advances in semantic coding and processing.

Contribution

This paper presents the SeIQA dataset and reports on the challenge's methods and results, establishing a new benchmark for human-oriented semantic image quality assessment.

Findings

6 teams submitted solutions achieving SOTA performance

The dataset includes 750 image pairs across training, validation, and testing

The challenge promotes semantic coding and optimization research

Abstract

This paper reviews the LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment. This challenge aims to raise a new direction, i.e., how to evaluate the loss of semantic information from the human perspective, intending to promote the development of some new directions, like semantic coding, processing, and semantic-oriented optimization, etc. Unlike existing datasets of quality assessment, we form a dataset of human-oriented semantic quality assessment, termed the SeIQA dataset. This dataset is divided into three parts for this competition: (i) training data: 510 pairs of degraded images and their corresponding ground truth references; (ii) validation data: 80 pairs of degraded images and their corresponding ground-truth references; (iii) testing data: 160 pairs of degraded images and their corresponding ground-truth references. The primary objective of this challenge is to establish a new and powerful benchmark for human-oriented semantic image quality assessment. There are a total of 58 teams registered in this competition, and 6 teams submitted valid solutions and fact sheets for the final testing phase. These submissions achieved state-of-the-art (SOTA) performance on the SeIQA dataset.