Small objects detection is a challenging task in computer vision due to the limited semantic information that can be extracted and susceptibility background interference. In this paper, we propose decoupled multi-scale small object algorithm named DMS-YOLOv5. The incorporates receptive field module into feature extraction network for better focus on low-resolution objects. coordinate attention ...

Faster RCNN has achieved great success for generic object detection including PASCAL object detection and MS COCO object detection. In this report, we propose a detailed designed Faster RCNN method named FDNet1.0 for face detection. Several techniques were employed including multi-scale training, multi-scale testing, light-designed RCNN, some tricks for inference and a vote-based ensemble metho...

Multi-scale geometrical and topological analyses of point clouds can reveal their rich structures. Because conformal alpha shapes of point clouds are hierarchical shapes under different mesh resolution or internal alpha values, their surface curvature estimations are one of the multi-scale geometrical analyses. We present a robust method for computing surface curvature of conformal alpha shapes...

The goal of multi-frame image super-resolution is to use information from low-resolution images to construct highresolution images. Current multi-frame image super-resolution methods are highly sensitive to prominent large scale artifacts found within the low-resolution images, leading to reduced image quality. This paper presents a novel adaptive approach to large scale artifact reduction in m...