Spatial-Frequency Aware for Object Detection in RAW Image

TL;DR

This paper introduces SFAE, a novel framework that enhances RAW image object detection by combining spatial and frequency domain features, improving detail recovery and detection accuracy.

Contribution

The paper proposes a new method that transforms frequency bands into spatial maps, enabling effective cross-domain fusion and adaptive adjustments for RAW image detection.

Findings

Improved object detection accuracy on RAW images.

Effective recovery of suppressed details in RAW data.

Enhanced feature representation through spatial-frequency fusion.

Abstract

Direct RAW-based object detection offers great promise by utilizing RAW data (unprocessed sensor data), but faces inherent challenges due to its wide dynamic range and linear response, which tends to suppress crucial object details. In particular, existing enhancement methods are almost all performed in the spatial domain, making it difficult to effectively recover these suppressed details from the skewed pixel distribution of RAW images. To address this limitation, we turn to the frequency domain, where features, such as object contours and textures, can be naturally separated based on frequency. In this paper, we propose Space-Frequency Aware RAW Image Object Detection Enhancer (SFAE), a novel framework that synergizes spatial and frequency representations. Our contribution is threefold. The first lies in the ``spatialization" of frequency bands. Different from the traditional paradigm of directly manipulating abstract spectra in deep networks, our method inversely transforms individual frequency bands back into tangible spatial maps, thus preserving direct physical intuition. Then the cross-domain fusion attention module is developed to enable deep multimodal interactions between these maps and the original spatial features. Finally, the framework performs adaptive nonlinear adjustments by predicting and applying different gamma parameters for the two domains.