Paper4 [Paper Review] GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving 논문 : GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving URL : arxiv.org/abs/1903.10955 GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving We present an efficient 3D object detection framework based on a single RGB image in the scenario of autonomous driving. Our efforts are put on extracting the underlying 3D information in a 2D image and determining the.. 2021. 5. 1. [Paper Review] Disentangling Monocular 3D Object Detection (MonoDis) 논문 : Disentangling Monocular 3D Object Detection (MonoDis) URL : arxiv.org/abs/1905.12365 Disentangling Monocular 3D Object Detection In this paper we propose an approach for monocular 3D object detection from a single RGB image, which leverages a novel disentangling transformation for 2D and 3D detection losses and a novel, self-supervised confidence score for 3D bounding boxes. Our pro arxiv.o.. 2021. 5. 1. [Papers Review] Parallel Tracking and Mapping for Small AR Workspaces(PTAM) 논문 : Parallel Tracking and Mapping for Small AR Workspaces (PTAM) URL : ieeexplore.ieee.org/document/4538852 Parallel Tracking and Mapping for Small AR Workspaces This paper presents a method of estimating camera pose in an unknown scene. While this has previously been attempted by adapting SLAM algorithms developed for robotic exploration, we propose a system specifically designed to track a ha.. 2021. 5. 1. [Papers Review] ArcFace: Additive Angular Margin Loss for Deep Face Recognition 논문 : ArcFace: Additive Angular Margin Loss for Deep Face Recognition(2019) , CVPR URL : https://arxiv.org/abs/1801.07698 ArcFace: Additive Angular Margin Loss for Deep Face Recognition One of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for large-scale face recognition is the design of appropriate loss functions that enhance discriminative power. Centr.. 2020. 10. 11. 이전 1 다음 반응형
