5 code implementations • ECCV 2020 • Kang Kim, Hee Seok Lee
In this paper we propose a novel anchor assignment strategy that adaptively separates anchors into positive and negative samples for a ground truth bounding box according to the model's learning status such that it is able to reason about the separation in a probabilistic manner.
Ranked #56 on Object Detection on COCO test-dev
no code implementations • 27 Feb 2018 • Hee Seok Lee, Kang Kim
By formulating the boundary estimation problem as a CNN-based pose and shape prediction task, our method is end-to-end trainable, and more robust to occlusion and small targets than other boundary estimation methods that rely on contour estimation or image segmentation.
no code implementations • CVPR 2013 • Hee Seok Lee, Kuoung Mu Lee
Therefore, enhancing image resolution can be an effective solution for securing the accuracy as well as the resolution of 3D reconstruction.
no code implementations • CVPR 2013 • Hee Seok Lee, Kuoung Mu Lee
Motion blur frequently occurs in dense 3D reconstruction using a single moving camera, and it degrades the quality of the 3D reconstruction.