arXiv Computer Vision research summaries for April 14, 2024.

Today's Research Themes (AI-Generated):

• Cross-modality fusion enhances object detection with Fusion-Mamba, outperforming state-of-the-art methods on public datasets.

• StreakNet-Arch introduces a real-time architecture for underwater LiDAR-Radar imaging, significantly improving scatter suppression.

• Coreset Selection for Object Detection (CSOD) demonstrates superior performance in selecting representative subsets for object detection tasks.

• LoopAnimate advances video generation with seamless looping capabilities, extending single-pass generation length while maintaining high quality.

• HANet and CGNet introduce novel networks for change detection, achieving improved performance with bitemporal very-high-resolution remote sensing images.