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.
Abstract (translated)
基于RAW数据的直接对象检测方法通过利用未经处理的传感器数据（即RAW数据）展现出了巨大的潜力，但同时也面临着固有的挑战。这些挑战主要来源于RAW图像具有宽广的动态范围和线性响应特性，这往往会抑制关键物体细节的有效显示。现有的增强方法几乎都集中在空间域内进行操作，难以从RAW图像中扭曲的像素分布中有效地恢复被压制的关键对象细节。 为了解决这一限制，我们转向了频域，在该领域中可以根据频率自然地分离出特征（如物体轮廓和纹理），这在空间域中较难实现。在此基础上，本文提出了一种新颖的框架——空间-频域感知RAW图像对象检测增强器(SFAE)，它融合了空间与频域表示。 我们的贡献主要体现在三个方面：第一，在“空间化”频率带宽方面，不同于传统深度网络直接操作抽象光谱的方法，我们逆向将各个频率带转换回具体的物理映射（即空间图），从而保持直观的物理理解；第二，开发了一种跨领域融合注意力模块，以促进这些频域生成的空间图与原始空间特征之间的深层多模态交互；第三，在两个域中进行自适应非线性调整：通过预测和应用不同的伽马参数来增强图像质量。 总的来说，SFAE框架旨在利用频域的优势，并结合空间信息，从而提升RAW数据驱动的对象检测性能。
URL
https://arxiv.org/abs/2508.01396
