DetectSCI：面向高分辨率视频快照压缩成像的目标引导感兴趣区域重建
DetectSCI: Toward Object-Guided ROI Reconstruction for High-Resolution Video Snapshot Compressive Imaging
将目标检测引入SCI重建流程，仅对检测到的ROI进行高分辨率重建，为高分辨率视频SCI提供了一种可扩展的按需重建范式；其Mamba-隐式模块与频率Mamba查询选择机制可复用于其他需要从混叠测量中恢复判别性特征的底层视觉任务。
原文依据 we propose DetectSCI, the first framework enabling object-guided region-of-interest (ROI) reconstruction for high-resolution SCI
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视频快照压缩成像（SCI）通过将多帧编码为单张二维测量，为高速相机提供了一种有前景的替代方案。然而，SCI需要算法来重建高速视频，且随着分辨率提高，重建变得计算昂贵且内存密集。大量资源被浪费在恢复包含很少有用信息的大片背景区域上，这凸显了选择性、目标驱动重建的需求。由于编码曝光引入的时空混叠，现有目标检测器难以在SCI测量上准确执行。为应对这一挑战，我们提出DetectSCI，这是首个实现高分辨率SCI目标引导感兴趣区域（ROI）重建的框架。内部检测器包含两个关键组件：由权重共享的Mamba隐式模块（MIM）构建的编码器用于渐进式特征细化，以及专用于频率感知查询选择的频率Mamba（FM）模块。MIM通过多尺度空洞卷积和隐式表示增强特征，而FM通过分解和重加权频带恢复判别性细节。在SportsMOT数据集上的实验表明，DetectSCI达到80.9平均精度（AP），至少超过最佳基于CNN的检测器2.8 AP，至少超过最佳基于Transformer的检测器4.1 AP，同时保持相当效率。代码将公开。
英文原文摘要 1486 字符
Video snapshot compressive imaging (SCI) offers a promising alternative to high-speed cameras by encoding multiple frames into a single 2D measurement. However, SCI requires algorithms to reconstruct the high-speed video, and as resolution increases, reconstruction becomes computationally expensive and memory-intensive. Much of the resource is wasted on recovering large background regions that contain little useful information, highlighting the need for selective, object-driven reconstruction. Existing object detectors struggle to perform accurately on SCI measurements due to the spatial-temporal aliasing introduced by coded exposure. To address this challenge, we propose DetectSCI, the first framework enabling object-guided region-of-interest (ROI) reconstruction for high-resolution SCI. The inside detector comprises two key components: an encoder built from weight-sharing Mamba-Implicit Modules (MIM) for progressive feature refinement, and a Frequency Mamba (FM) module dedicated to frequency-aware query selection. MIM enhances features via multi-scale dilated convolutions and implicit representations, while FM restores discriminative details by decomposing and reweighting frequency bands. Experiments on the SportsMOT dataset show that DetectSCI achieves 80.9 Average Precision (AP), surpassing the best CNN-based detector by at least 2.8 AP and the best Transformer-based detector by at least 4.1 AP, while maintaining comparable efficiency. Code will be released.