NVAutoNet: Fast and Accurate 360$^{\circ}$ 3D Visual Perception For Self Driving

no code implementations • 23 Mar 2023 • Trung Pham, Mehran Maghoumi, Wanli Jiang, Bala Siva Sashank Jujjavarapu, Mehdi Sajjadi, Xin Liu, Hsuan-Chu Lin, Bor-Jeng Chen, Giang Truong, Chao Fang, Junghyun Kwon, Minwoo Park

Achieving robust and real-time 3D perception is fundamental for autonomous vehicles.

Autonomous Vehicles Computational Efficiency

Confidence Propagation Cluster: Unleash Full Potential of Object Detectors

1 code implementation • CVPR 2022 • Yichun Shen, Wanli Jiang, Zhen Xu, Rundong Li, Junghyun Kwon, Siyi Li

It has been a long history that most object detection methods obtain objects by using the non-maximum suppression (NMS) and its improved versions like Soft-NMS to remove redundant bounding boxes.

Object object-detection +1

Deep View Morphing

no code implementations • CVPR 2017 • Dinghuang Ji, Junghyun Kwon, Max McFarland, Silvio Savarese

An encoder-decoder network then generates dense correspondences between the rectified images and blending masks to predict the visibility of pixels of the rectified images in the middle view.