HipyrNet: Hypernet-Guided Feature Pyramid network for mixed-exposure correction

2025-01-09

AI Summary

To address detail loss and contrast imbalance caused by extreme brightness variations in mixed-exposure images, this paper proposes an adaptive feature decomposition and reconstruction framework integrating Laplacian pyramids with hypernetworks. The method decomposes input images into multi-scale Laplacian layers and reconstructs them via a dynamic, image-adaptive process. Its key contributions are: (1) the first incorporation of hypernetworks into structured exposure correction, enabling dynamic generation of scale-specific Laplacian decomposition kernels tailored to each input; and (2) the integration of dynamic convolution and multi-scale feature fusion to enhance reconstruction fidelity. Extensive evaluation on challenging extreme-exposure scenarios demonstrates significant improvements over state-of-the-art methods—achieving higher PSNR and SSIM scores—while qualitatively yielding more natural luminance transitions and superior recovery of fine textures.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Recent advancements in image translation for enhancing mixed-exposure images have demonstrated the transformative potential of deep learning algorithms. However, addressing extreme exposure variations in images remains a significant challenge due to the inherent complexity and contrast inconsistencies across regions. Current methods often struggle to adapt effectively to these variations, resulting in suboptimal performance. In this work, we propose HipyrNet, a novel approach that integrates a HyperNetwork within a Laplacian Pyramid-based framework to tackle the challenges of mixed-exposure image enhancement. The inclusion of a HyperNetwork allows the model to adapt to these exposure variations. HyperNetworks dynamically generates weights for another network, allowing dynamic changes during deployment. In our model, the HyperNetwork employed is used to predict optimal kernels for Feature Pyramid decomposition, which enables a tailored and adaptive decomposition process for each input image. Our enhanced translational network incorporates multiscale decomposition and reconstruction, leveraging dynamic kernel prediction to capture and manipulate features across varying scales. Extensive experiments demonstrate that HipyrNet outperforms existing methods, particularly in scenarios with extreme exposure variations, achieving superior results in both qualitative and quantitative evaluations. Our approach sets a new benchmark for mixed-exposure image enhancement, paving the way for future research in adaptive image translation.

Problem

• High Dynamic Range Imaging
• Contrast Adjustment
• Lighting Correction

Innovation

• HipyrNet
• HyperNetwork
• Laplacian Pyramid