Match!

ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection

Published on Feb 7, 2020 in AAAI (National Conference on Artificial Intelligence)
Zhenbo Xu2
Estimated H-index: 2
(USTC: University of Science and Technology of China),
Wei Zhang2
Estimated H-index: 2
(Baidu)
+ 6 AuthorsLiusheng Huang8
Estimated H-index: 8
(USTC: University of Science and Technology of China)
Abstract
  • References (0)
  • Citations (4)
馃摉 Papers frequently viewed together
2018ICML: International Conference on Machine Learning
6 Authors (Haiguang Wen, ..., Zhongming Liu)
7 Citations
2016BMVC: British Machine Vision Conference
5 Authors (Luwei Yang, ..., Ping Tan)
2 Citations
2016BMVC: British Machine Vision Conference
18 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
References0
Newest
Cited By4
Newest
Jun 14, 2020 in CVPR (Computer Vision and Pattern Recognition)
#2Divyansh Garg (Cornell University)H-Index: 4
Last. Wei-Lun Chao (OSU: Ohio State University)H-Index: 14
view all 9 authors...
Reliable and accurate 3D object detection is a necessity for safe autonomous driving. Although LiDAR sensors can provide accurate 3D point cloud estimates of the environment, they are also prohibitively expensive for many settings. Recently, the introduction of pseudo-LiDAR (PL) has led to a drastic reduction in the accuracy gap between methods based on LiDAR sensors and those based on cheap stereo cameras. PL combines state-of-the-art deep neural networks for 3D depth estimation with those for ...
Jun 14, 2020 in CVPR (Computer Vision and Pattern Recognition)
Last. Hujun Bao
view all 7 authors...
In this paper, we propose a novel system named Disp R-CNN for 3D object detection from stereo images. Many recent works solve this problem by first recovering a point cloud with disparity estimation and then apply a 3D detector. The disparity map is computed for the entire image, which is costly and fails to leverage category-specific prior. In contrast, we design an instance disparity estimation network (iDispNet) that predicts disparity only for pixels on objects of interest and learns a categ...
#2Divyansh Garg (Cornell University)H-Index: 4
Last. Wei-Lun Chao (OSU: Ohio State University)H-Index: 14
view all 9 authors...
Reliable and accurate 3D object detection is a necessity for safe autonomous driving. Although LiDAR sensors can provide accurate 3D point cloud estimates of the environment, they are also prohibitively expensive for many settings. Recently, the introduction of pseudo-LiDAR (PL) has led to a drastic reduction in the accuracy gap between methods based on LiDAR sensors and those based on cheap stereo cameras. PL combines state-of-the-art deep neural networks for 3D depth estimation with those for ...
In this paper, we propose a novel system named Disp R-CNN for 3D object detection from stereo images. Many recent works solve this problem by first recovering a point cloud with disparity estimation and then apply a 3D detector. The disparity map is computed for the entire image, which is costly and fails to leverage category-specific prior. In contrast, we design an instance disparity estimation network (iDispNet) that predicts disparity only for pixels on objects of interest and learns a categ...