Unified-EGformer: Exposure Guided Lightweight Transformer for Mixed-Exposure Image Enhancement

TL;DR

Unified-EGformer is a lightweight transformer model designed for real-time mixed exposure image enhancement, effectively addressing overexposure and underexposure with high efficiency and minimal fine-tuning.

Contribution

The paper introduces a novel exposure-guided transformer architecture that combines local and global refinement for enhanced mixed exposure image correction.

Findings

Achieves real-time processing with 95 ms inference time.

Uses only 0.1 million parameters, enabling lightweight deployment.

Demonstrates high generalizability across various datasets and tasks.

Abstract

Despite recent strides made by AI in image processing, the issue of mixed exposure, pivotal in many real-world scenarios like surveillance and photography, remains inadequately addressed. Traditional image enhancement techniques and current transformer models are limited with primary focus on either overexposure or underexposure. To bridge this gap, we introduce the Unified-Exposure Guided Transformer (Unified-EGformer). Our proposed solution is built upon advanced transformer architectures, equipped with local pixel-level refinement and global refinement blocks for color correction and image-wide adjustments. We employ a guided attention mechanism to precisely identify exposure-compromised regions, ensuring its adaptability across various real-world conditions. U-EGformer, with a lightweight design featuring a memory footprint (peak memory) of only $\sim$1134 MB (0.1 Million parameters) and an inference time of 95 ms (9.61x faster than the average), is a viable choice for real-time applications such as surveillance and autonomous navigation. Additionally, our model is highly generalizable, requiring minimal fine-tuning to handle multiple tasks and datasets with a single architecture.