Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Xinzhu Ma

Xinzhu Ma

Geometry Uncertainty Projection Network for Monocular 3D Object Detection


Aug 13, 2021
Yan Lu, Xinzhu Ma, Lei Yang, Tianzhu Zhang, Yating Liu, Qi Chu, Junjie Yan, Wanli Ouyang

Figure 1 for Geometry Uncertainty Projection Network for Monocular 3D Object Detection
Figure 2 for Geometry Uncertainty Projection Network for Monocular 3D Object Detection
Figure 3 for Geometry Uncertainty Projection Network for Monocular 3D Object Detection
Figure 4 for Geometry Uncertainty Projection Network for Monocular 3D Object Detection
* To appear at ICCV2021 
  Access Paper or Ask Questions

Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection


Jul 29, 2021
Yinmin Zhang, Xinzhu Ma, Shuai Yi, Jun Hou, Zhihui Wang, Wanli Ouyang, Dan Xu

Figure 1 for Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection
Figure 2 for Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection
Figure 3 for Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection
Figure 4 for Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection
* 16 pages, 11 figures 
  Access Paper or Ask Questions

Delving into Localization Errors for Monocular 3D Object Detection


Mar 30, 2021
Xinzhu Ma, Yinmin Zhang, Dan Xu, Dongzhan Zhou, Shuai Yi, Haojie Li, Wanli Ouyang

Figure 1 for Delving into Localization Errors for Monocular 3D Object Detection
Figure 2 for Delving into Localization Errors for Monocular 3D Object Detection
Figure 3 for Delving into Localization Errors for Monocular 3D Object Detection
Figure 4 for Delving into Localization Errors for Monocular 3D Object Detection
* CVPR'2021, code will be made available 
  Access Paper or Ask Questions

Rethinking Pseudo-LiDAR Representation


Aug 11, 2020
Xinzhu Ma, Shinan Liu, Zhiyi Xia, Hongwen Zhang, Xingyu Zeng, Wanli Ouyang

Figure 1 for Rethinking Pseudo-LiDAR Representation
Figure 2 for Rethinking Pseudo-LiDAR Representation
Figure 3 for Rethinking Pseudo-LiDAR Representation
Figure 4 for Rethinking Pseudo-LiDAR Representation
* ECCV2020. Supplemental Material attached 
  Access Paper or Ask Questions

Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving


Apr 01, 2019
Xinzhu Ma, Zhihui Wang, Haojie Li, Wanli Ouyang, Pengbo Zhang

Figure 1 for Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
Figure 2 for Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
Figure 3 for Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
Figure 4 for Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
* arXiv admin note: text overlap with arXiv:1711.06396 by other authors 
  Access Paper or Ask Questions

User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks


Aug 10, 2018
Yuanzheng Ci, Xinzhu Ma, Zhihui Wang, Haojie Li, Zhongxuan Luo

Figure 1 for User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks
Figure 2 for User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks
Figure 3 for User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks
Figure 4 for User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks
* Accepted for publication at the 2018 ACM Multimedia Conference (MM '18) 
  Access Paper or Ask Questions