PDE: Gene Effect Inspired Parameter Dynamic Evolution for Low-light Image Enhancement

2025-05-14

AI Summary

This paper identifies and names the “gene effect” in low-light image enhancement (LLIE): static model parameters—often randomly initialized—frequently underperform their randomly initialized counterparts, limiting overall model performance. To address this, we propose a parameter dynamic evolution framework inspired by biological evolution, enabling image-level personalized parameter generation via orthogonal initialization, gene-recombination-based parameter composition, mutation-inspired perturbation, and a lightweight dynamic modulation module. This work is the first to systematically integrate evolutionary principles into LLIE, significantly enhancing model adaptability to diverse low-light conditions. Extensive experiments demonstrate state-of-the-art performance on benchmarks including LOL and DARK, achieving PSNR gains of 1.2–2.4 dB and SSIM improvements of 0.018–0.032 over prior methods, with less than 3% additional inference overhead.

Technology Category

• Machine Learning: Evolutionary Learning
• Search and Optimization: Learning to Search
• Computer Vision: Low Level & Physics-based Vision

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Low-light image enhancement (LLIE) is a fundamental task in computational photography, aiming to improve illumination, reduce noise, and enhance image quality. While recent advancements focus on designing increasingly complex neural network models, we observe a peculiar phenomenon: resetting certain parameters to random values unexpectedly improves enhancement performance for some images. Drawing inspiration from biological genes, we term this phenomenon the gene effect. The gene effect limits enhancement performance, as even random parameters can sometimes outperform learned ones, preventing models from fully utilizing their capacity. In this paper, we investigate the reason and propose a solution. Based on our observations, we attribute the gene effect to static parameters, analogous to how fixed genetic configurations become maladaptive when environments change. Inspired by biological evolution, where adaptation to new environments relies on gene mutation and recombination, we propose parameter dynamic evolution (PDE) to adapt to different images and mitigate the gene effect. PDE employs a parameter orthogonal generation technique and the corresponding generated parameters to simulate gene recombination and gene mutation, separately. Experiments validate the effectiveness of our techniques. The code will be released to the public.

Problem

• Investigates the gene effect limiting low-light image enhancement performance
• Proposes dynamic parameter evolution to adapt to different image conditions
• Addresses static parameter limitations via biological-inspired mutation and recombination

Innovation

• Parameter Dynamic Evolution (PDE) for image enhancement
• Gene-inspired parameter orthogonal generation technique
• Dynamic adaptation to mitigate static parameter limitations