Search papers, labs, and topics across Lattice.
This paper introduces FreqAdapt, a novel lightweight module that enhances RAW object detection by processing data in the frequency domain rather than the traditional spatial domain. By mapping Image Signal Processor (ISP) operations to the Fourier frequency domain and employing an adaptive frequency domain encoder, FreqAdapt optimally utilizes the unique characteristics of RAW images to improve detection performance in challenging conditions. Experimental results show that FreqAdapt achieves state-of-the-art performance across various datasets while remaining efficient and interpretable, making it a valuable addition to existing object detection frameworks.
FreqAdapt transforms RAW object detection by leveraging frequency domain processing, achieving state-of-the-art results even in adverse conditions.
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.
