Bilevel Generative Learning for Low-Light Vision

TL;DR

This paper introduces a novel bilevel generative learning framework for low-light vision tasks, using a generative RAW-to-RGB conversion block to unify and improve performance across enhancement, detection, and segmentation.

Contribution

It proposes the first bilevel model linking data generation with vision tasks, enabling a generic and effective low-light vision solution.

Findings

Outperforms existing methods in low-light enhancement, detection, and segmentation.

Demonstrates strong generalization ability across different low-light vision tasks.

Provides a flexible bilevel learning paradigm with low cost and high accuracy options.

Abstract

Recently, there has been a growing interest in constructing deep learning schemes for Low-Light Vision (LLV). Existing techniques primarily focus on designing task-specific and data-dependent vision models on the standard RGB domain, which inherently contain latent data associations. In this study, we propose a generic low-light vision solution by introducing a generative block to convert data from the RAW to the RGB domain. This novel approach connects diverse vision problems by explicitly depicting data generation, which is the first in the field. To precisely characterize the latent correspondence between the generative procedure and the vision task, we establish a bilevel model with the parameters of the generative block defined as the upper level and the parameters of the vision task defined as the lower level. We further develop two types of learning strategies targeting different goals, namely low cost and high accuracy, to acquire a new bilevel generative learning paradigm. The generative blocks embrace a strong generalization ability in other low-light vision tasks through the bilevel optimization on enhancement tasks. Extensive experimental evaluations on three representative low-light vision tasks, namely enhancement, detection, and segmentation, fully demonstrate the superiority of our proposed approach. The code will be available at https://github.com/Yingchi1998/BGL.