🤖 AI Summary
This work addresses the limitation of existing object detection methods that predominantly operate on sRGB images while overlooking the superior noise characteristics and richer information inherent in RAW sensor data, particularly under low-light and adverse weather conditions. To bridge this gap, we propose FreqAdapt—a lightweight frequency-domain adaptive enhancement module—that, for the first time, decomposes and transfers in-camera ISP operations into the Fourier domain based on their physical properties, enabling principled domain separation. By jointly modeling magnitude spectra, phase spectra, and RAW features through a learnable fusion mechanism and a frequency-domain encoder, our approach achieves global context-guided adaptive enhancement. Extensive experiments demonstrate that FreqAdapt significantly improves detection performance across diverse lighting and weather conditions, offering a lightweight, efficient, and physically interpretable solution that seamlessly integrates into existing detection frameworks.
📝 Abstract
Existing object detection methods predominantly utilize sRGB inputs, which are compressed from RAW sensor data using Image Signal Processors (ISP) originally designed for visualization purposes. Compared to RGB images, RAW images possess favorable noise characteristics and richer information representation, which are crucial for object detection, particularly under challenging conditions such as adverse weather or low-light environments. In this paper, we propose FreqAdapt, a lightweight module for adaptive RAW data enhancement in the frequency domain. Unlike traditional spatial domain processing methods, FreqAdapt innovatively maps ISP operations to the Fourier frequency domain and performs domain separation based on the physical properties of ISP operations, ensuring each operation is performed in its most suitable domain. Meanwhile, through an adaptive frequency domain encoder that jointly analyzes amplitude spectrum, phase spectrum, and RAW image features, we provide global context for ISP parameter prediction and employ a learnable fusion mechanism to achieve adaptive feature enhancement. Extensive experiments on multiple datasets with diverse lighting and weather conditions demonstrate that FreqAdapt achieves state-of-the-art performance while maintaining lightweight efficiency and good physical interpretability. Furthermore, our module can be seamlessly incorporated into existing object detection frameworks, providing a novel solution for visual perception tasks in the RAW domain.