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

arXiv:2604.21743v1 Announce Type: new 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.

Related

• OSC: Hardware Efficient W4A4 Quantization via Outlier Separation in Channel Dimension
• From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization
• Efficient Semantic Image Communication for Traffic Monitoring at the Edge
• Lightweight Low-Light Image Enhancement via Distribution-Normalizing Preprocessing and Depthwise U-Net
• DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models

Source: arXiv cs.AI | 2026-04-24