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 Hongyang Li

Hongyang Li

BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision


Nov 18, 2022
Chenyu Yang, Yuntao Chen, Hao Tian, Chenxin Tao, Xizhou Zhu, Zhaoxiang Zhang, Gao Huang, Hongyang Li, Yu Qiao, Lewei Lu, Jie Zhou, Jifeng Dai

Figure 1 for BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
Figure 2 for BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
Figure 3 for BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
Figure 4 for BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Stare at What You See: Masked Image Modeling without Reconstruction


Nov 16, 2022
Hongwei Xue, Peng Gao, Hongyang Li, Yu Qiao, Hao Sun, Houqiang Li, Jiebo Luo

Figure 1 for Stare at What You See: Masked Image Modeling without Reconstruction
Figure 2 for Stare at What You See: Masked Image Modeling without Reconstruction
Figure 3 for Stare at What You See: Masked Image Modeling without Reconstruction
Figure 4 for Stare at What You See: Masked Image Modeling without Reconstruction

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation


Oct 11, 2022
Hongyang Li, Jiehong Lin, Kui Jia

Figure 1 for DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
Figure 2 for DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
Figure 3 for DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
Figure 4 for DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
* ECCV 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe


Sep 12, 2022
Hongyang Li, Chonghao Sima, Jifeng Dai, Wenhai Wang, Lewei Lu, Huijie Wang, Enze Xie, Zhiqi Li, Hanming Deng, Hao Tian, Xizhou Zhu, Li Chen, Yulu Gao, Xiangwei Geng, Jia Zeng, Yang Li, Jiazhi Yang, Xiaosong Jia, Bohan Yu, Yu Qiao, Dahua Lin, Si Liu, Junchi Yan, Jianping Shi, Ping Luo

Figure 1 for Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
Figure 2 for Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
Figure 3 for Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
Figure 4 for Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning


Jul 18, 2022
Shengchao Hu, Li Chen, Penghao Wu, Hongyang Li, Junchi Yan, Dacheng Tao

Figure 1 for ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning
Figure 2 for ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning
Figure 3 for ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning
Figure 4 for ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning
* ECCV 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot


Jun 16, 2022
Li Chen, Tutian Tang, Zhitian Cai, Yang Li, Penghao Wu, Hongyang Li, Jianping Shi, Junchi Yan, Yu Qiao

Figure 1 for Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot
Figure 2 for Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot
Figure 3 for Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot
Figure 4 for Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot
* Tech report. Project page: https://github.com/OpenPerceptionX/Openpilot-Deepdive 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline


Jun 16, 2022
Penghao Wu, Xiaosong Jia, Li Chen, Junchi Yan, Hongyang Li, Yu Qiao

Figure 1 for Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline
Figure 2 for Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline
Figure 3 for Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline
Figure 4 for Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline
* 15 pages, 7 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark


Apr 12, 2022
Li Chen, Chonghao Sima, Yang Li, Zehan Zheng, Jiajie Xu, Xiangwei Geng, Hongyang Li, Conghui He, Jianping Shi, Yu Qiao, Junchi Yan

Figure 1 for PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
Figure 2 for PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
Figure 3 for PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
Figure 4 for PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
* Update project page: https://github.com/OpenPerceptionX/PersFormer_3DLane | OpenLane dataset: https://github.com/OpenPerceptionX/OpenLane 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers


Mar 31, 2022
Zhiqi Li, Wenhai Wang, Hongyang Li, Enze Xie, Chonghao Sima, Tong Lu, Qiao Yu, Jifeng Dai

Figure 1 for BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers
Figure 2 for BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers
Figure 3 for BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers
Figure 4 for BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers
* 20 pages, 9 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space


Nov 14, 2021
Jiehong Lin, Hongyang Li, Ke Chen, Jiangbo Lu, Kui Jia

Figure 1 for Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space
Figure 2 for Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space
Figure 3 for Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space
Figure 4 for Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space
* Accepted by NeurIPS 2021 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>