ModalFormer: Multimodal Transformer for Low-Light Image Enhancement

TL;DR

ModalFormer is a novel multimodal transformer framework that leverages nine auxiliary modalities to significantly improve low-light image enhancement, outperforming existing methods on benchmark datasets.

Contribution

Introduces ModalFormer, the first large-scale multimodal framework for LLIE that integrates nine auxiliary modalities using a novel cross-modal self-attention mechanism.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Effectively fuses diverse modalities for enhanced image restoration.

Demonstrates robustness across various low-light conditions.

Abstract

Low-light image enhancement (LLIE) is a fundamental yet challenging task due to the presence of noise, loss of detail, and poor contrast in images captured under insufficient lighting conditions. Recent methods often rely solely on pixel-level transformations of RGB images, neglecting the rich contextual information available from multiple visual modalities. In this paper, we present ModalFormer, the first large-scale multimodal framework for LLIE that fully exploits nine auxiliary modalities to achieve state-of-the-art performance. Our model comprises two main components: a Cross-modal Transformer (CM-T) designed to restore corrupted images while seamlessly integrating multimodal information, and multiple auxiliary subnetworks dedicated to multimodal feature reconstruction. Central to the CM-T is our novel Cross-modal Multi-headed Self-Attention mechanism (CM-MSA), which effectively fuses RGB data with modality-specific features--including deep feature embeddings, segmentation information, geometric cues, and color information--to generate information-rich hybrid attention maps. Extensive experiments on multiple benchmark datasets demonstrate ModalFormer's state-of-the-art performance in LLIE. Pre-trained models and results are made available at https://github.com/albrateanu/ModalFormer.