Spatial-Frequency Aware for Object Detection in RAW Image
By: Zhuohua Ye, Liming Zhang, Hongru Han
Potential Business Impact:
Improves camera vision by enhancing hidden details.
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.
Similar Papers
A Spatial-Frequency Aware Multi-Scale Fusion Network for Real-Time Deepfake Detection
CV and Pattern Recognition
Finds fake videos fast, even on phones.
SFFR: Spatial-Frequency Feature Reconstruction for Multispectral Aerial Object Detection
CV and Pattern Recognition
Helps drones see better in different light.
Towards Generalizable Deepfake Detection with Spatial-Frequency Collaborative Learning and Hierarchical Cross-Modal Fusion
CV and Pattern Recognition
Finds fake videos better, even new kinds.