Bridging the Training-Deployment Gap: Gated Encoding and Multi-Scale Refinement for Efficient Quantization-Aware Image Enhancement

TL;DR

This paper introduces a mobile-friendly image enhancement model using hierarchical architecture, gated encoding, multiscale refinement, and Quantization-Aware Training to ensure high quality and efficiency in low-precision deployment.

Contribution

It presents a novel hierarchical network with gated encoder blocks and multiscale refinement, specifically designed for effective quantization-aware mobile image enhancement.

Findings

Achieves high-fidelity image enhancement on mobile devices.

Maintains low computational overhead with quantization-aware training.

Prevents quality degradation typically seen with post-training quantization.

Abstract

Image enhancement models for mobile devices often struggle to balance high output quality with the fast processing speeds required by mobile hardware. While recent deep learning models can enhance low-quality mobile photos into high-quality images, their performance is often degraded when converted to lower-precision formats for actual use on mobile phones. To address this training-deployment mismatch, we propose an efficient image enhancement model designed specifically for mobile deployment. Our approach uses a hierarchical network architecture with gated encoder blocks and multiscale refinement to preserve fine-grained visual features. Moreover, we incorporate Quantization-Aware Training (QAT) to simulate the effects of low-precision representation during the training process. This allows the network to adapt and prevents the typical drop in quality seen with standard post-training quantization (PTQ). Experimental results demonstrate that the proposed method produces high-fidelity visual output while maintaining the low computational overhead needed for practical use on standard mobile devices. The code will be available at https://github.com/GenAI4E/QATIE.git.