Xiaowei Zhou

PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos

Jun 15, 2022
Yiming Xie, Matheus Gadelha, Fengting Yang, Xiaowei Zhou, Huaizu Jiang

Figure 2 for PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos

Figure 3 for PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos

Figure 4 for PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos

* CVPR 2022. Project page: https://neu-vi.github.io/planarrecon/

Access Paper or Ask Questions

Latent Boundary-guided Adversarial Training

Jun 08, 2022
Xiaowei Zhou, Ivor W. Tsang, Jie Yin

Figure 2 for Latent Boundary-guided Adversarial Training

Figure 3 for Latent Boundary-guided Adversarial Training

Figure 4 for Latent Boundary-guided Adversarial Training

* To appear in Machine Learning

Access Paper or Ask Questions

Neural 3D Reconstruction in the Wild

May 25, 2022
Jiaming Sun, Xi Chen, Qianqian Wang, Zhengqi Li, Hadar Averbuch-Elor, Xiaowei Zhou, Noah Snavely

Figure 2 for Neural 3D Reconstruction in the Wild

Figure 3 for Neural 3D Reconstruction in the Wild

Figure 4 for Neural 3D Reconstruction in the Wild

* Accepted to SIGGRAPH 2022 (Conference Proceedings). Project page: https://zju3dv.github.io/neuralrecon-w/

Access Paper or Ask Questions

OnePose: One-Shot Object Pose Estimation without CAD Models

May 24, 2022
Jiaming Sun, Zihao Wang, Siyu Zhang, Xingyi He, Hongcheng Zhao, Guofeng Zhang, Xiaowei Zhou

Figure 2 for OnePose: One-Shot Object Pose Estimation without CAD Models

Figure 3 for OnePose: One-Shot Object Pose Estimation without CAD Models

Figure 4 for OnePose: One-Shot Object Pose Estimation without CAD Models

* Accepted to CVPR 2022. Project page: https://zju3dv.github.io/onepose/

Access Paper or Ask Questions

Neural 3D Scene Reconstruction with the Manhattan-world Assumption

May 18, 2022
Haoyu Guo, Sida Peng, Haotong Lin, Qianqian Wang, Guofeng Zhang, Hujun Bao, Xiaowei Zhou

Figure 2 for Neural 3D Scene Reconstruction with the Manhattan-world Assumption

Figure 3 for Neural 3D Scene Reconstruction with the Manhattan-world Assumption

Figure 4 for Neural 3D Scene Reconstruction with the Manhattan-world Assumption

* CVPR 2022 Oral. Project page: https://zju3dv.github.io/manhattan_sdf

Access Paper or Ask Questions

Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation

May 12, 2022
Jian Zhang, Yuanqing Zhang, Huan Fu, Xiaowei Zhou, Bowen Cai, Jinchi Huang, Rongfei Jia, Binqiang Zhao, Xing Tang

Figure 2 for Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation

Figure 3 for Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation

Figure 4 for Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation

Access Paper or Ask Questions

Modeling Indirect Illumination for Inverse Rendering

Apr 14, 2022
Yuanqing Zhang, Jiaming Sun, Xingyi He, Huan Fu, Rongfei Jia, Xiaowei Zhou

Figure 2 for Modeling Indirect Illumination for Inverse Rendering

Figure 3 for Modeling Indirect Illumination for Inverse Rendering

Figure 4 for Modeling Indirect Illumination for Inverse Rendering

Access Paper or Ask Questions

Semantic keypoint-based pose estimation from single RGB frames

Apr 12, 2022
Karl Schmeckpeper, Philip R. Osteen, Yufu Wang, Georgios Pavlakos, Kenneth Chaney, Wyatt Jordan, Xiaowei Zhou, Konstantinos G. Derpanis, Kostas Daniilidis

Figure 2 for Semantic keypoint-based pose estimation from single RGB frames

Figure 3 for Semantic keypoint-based pose estimation from single RGB frames

Figure 4 for Semantic keypoint-based pose estimation from single RGB frames

* Field Robotics, 2, 147-171, 2022
* https://sites.google.com/view/rcta-object-keypoints-dataset/home. arXiv admin note: substantial text overlap with arXiv:1703.04670

Access Paper or Ask Questions

Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation

Mar 29, 2022
Xiao Fu, Shangzhan Zhang, Tianrun Chen, Yichong Lu, Lanyun Zhu, Xiaowei Zhou, Andreas Geiger, Yiyi Liao

Figure 2 for Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation

Figure 3 for Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation

Figure 4 for Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation

* Project page: https://fuxiao0719.github.io/projects/panopticnerf/

Access Paper or Ask Questions