# LEIQ-Assessor: Multi-dimensional Quality Assessment of Low-light Enhanced Images via Multi-task Learning

arXiv: https://arxiv.org/abs/2606.29752 · HTML: https://mlsanity.com/paper/2606.29752/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 21 of 21)

- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [A Deep Learning based No-reference Quality Assessment Model for UGC Videos](https://mlsanity.com/paper/2204.14047/) (2022)
- [Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Training](https://mlsanity.com/paper/2105.14550/) (2021)
- [Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models](https://mlsanity.com/paper/2307.13981/) (2023)
- [LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models](https://mlsanity.com/paper/2408.14008/) (2024)
- [Large Multi-modality Model Assisted AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2404.17762/) (2024)
- [Enhancing Blind Video Quality Assessment with Rich Quality-aware Features](https://mlsanity.com/paper/2405.08745/) (2024)
- [Deep Neural Network for Blind Visual Quality Assessment of 4K Content](https://mlsanity.com/paper/2206.04363/) (2022)
- [Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Model](https://mlsanity.com/paper/2407.21408/) (2024)
- [VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning](https://mlsanity.com/paper/2508.06051/) (2025)
- [Assessing UHD Image Quality from Aesthetics, Distortions, and Saliency](https://mlsanity.com/paper/2409.00749/) (2024)
- [Dual-Branch Network for Portrait Image Quality Assessment](https://mlsanity.com/paper/2405.08555/) (2024)
- [Generalizable Video Quality Assessment via Weak-to-Strong Learning](https://mlsanity.com/paper/2505.03631/) (2025)
- [CompressedVQA-HDR: Generalized Full-reference and No-reference Quality Assessment Models for Compressed High Dynamic Range Videos](https://mlsanity.com/paper/2507.11900/) (2025)
- [Blind Multimodal Quality Assessment of Low-light Images](https://mlsanity.com/paper/2303.10369/) (2023)
- [Efficient Face Image Quality Assessment via Self-training and Knowledge Distillation](https://mlsanity.com/paper/2507.15709/) (2025)
- [QualiRAG: Retrieval-Augmented Generation for Visual Quality Understanding](https://mlsanity.com/paper/2601.18195/) (2026)

## Abstract (arXiv)

Low-light image enhancement algorithms (LIEAs) aim to improve the visibility of images captured under poor illumination. However, the enhancement process often introduces artifacts such as noise amplification, color shift, structural damage, and over-exposure, which degrade the perceptual quality of the enhanced images. Therefore, a reliable image quality assessment (IQA) metric for evaluating enhancement effects is of great importance for both the development of LIEAs and their practical applications. In this paper, we present LEIQ-Assessor, a multi-dimensional quality assessment model for low-light image enhancement based on multi-task learning, developed for the QoMEX 2026 Grand Challenge on Low-light Enhanced Image Quality Assessment. Specifically, our method leverages a pre-trained SigLIP2 Vision Transformer as the backbone and simultaneously predicts the overall Mean Opinion Score (MOS) together with six perceptual sub-attributes: lightness, color fidelity, noise level, exposure quality, naturalness, and content recovery. By jointly optimizing these correlated objectives via the PLCC loss, the shared representation captures richer quality-aware features than its single-task counterpart. Experiments on the MLE benchmark demonstrate that LEIQ-Assessor significantly outperforms existing no-reference IQA models and hand-crafted quality descriptors. Our method achieved second place in the QoMEX 2026 Grand Challenge on Low-light Enhanced Image Quality Assessment. The code is available at https://github.com/sunwei925/LEIQ-Assessor.