Both sides previous revision
Previous revision
Next revision
|
Previous revision
Next revision
Both sides next revision
|
members:wangr [2019/10/09 09:39] Rui Wang |
members:wangr [2021/12/26 16:16] Rui Wang |
| |
==== News ==== | ==== News ==== |
* [10.2018] The code for LDSO (Direct Sparse Odometry with Loop Closure) has been released! Please visit the [[https://vision.in.tum.de/research/vslam/ldso|project page]] for details. | * [12.2021] My new personal webpage [[https://rui2016.github.io|rui2016.github.io]] is online! |
| * [03.2021] I join the [[https://www.microsoft.com/en-us/research/lab/mixed-reality-ai-zurich/|Microsoft Mixed Reality & AI Lab Zurich]] as a senior research scientist. |
| * [03.2021] One paper accepted by ICRA, one paper accepted by CVPR (oral). |
| * [07.2020] Our paper "DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization" is accepted by ECCV 2020 (spotlight). Code is released and please check our [[https://vision.in.tum.de/research/vslam/dh3d|project page]] for details. |
| * [05.2020] We are organizing a workshop together with a challenge on [[https://sites.google.com/view/mlad-eccv2020|Map-based Localization for Autonomous Driving]] at ECCV 2020, Glasgow, UK. |
| * [05.2020] The results of Stereo DSO on KITTI Odometry test set are uploaded to the [[https://vision.in.tum.de/research/vslam/stereo-dso|project page]]. |
| * [02.2020] D3VO is accepted by CVPR 2020.([[https://arxiv.org/abs/2003.01060|arxiv]]) |
| * [01.2020] DirectShape has been accepted by ICRA 2020. It is an optimization pipeline that estimates the 3D poses and shapes of cars directly from a stereo image pair, no 3D points are needed. ([[https://vision.in.tum.de/research/vslam/direct-shape|project page]]) |
| * [10.2018] The code for LDSO (Direct Sparse Odometry with Loop Closure) has been released! ([[https://vision.in.tum.de/research/vslam/ldso|project page]]). |
* [07.2018] We have one paper accepted by ECCV'18 (oral) and two papers accepted by IROS'18. | * [07.2018] We have one paper accepted by ECCV'18 (oral) and two papers accepted by IROS'18. |
* [06-12.2018] I will be interning with Prof. Dieter Fox in the recently founded Nvidia Robotics Research Lab in Seattle. | * [06-12.2018] I will be interning with Prof. Dieter Fox in the Nvidia Robotics Research Lab in Seattle. |
* [05.2018] We have released our code for Online Photometric Calibration! Please find the link on the [[https://vision.in.tum.de/research/vslam/photometric-calibration|project page]]. The paper was recently nominated by ICRA'18 for the Best Vision Paper Award. | * [05.2018] We have released our code for Online Photometric Calibration! Please find the link on the [[https://vision.in.tum.de/research/vslam/photometric-calibration|project page]]. The paper was recently nominated by ICRA'18 for the Best Vision Paper Award. |
* [03.2018] I join [[https://www.artisense.ai/|Artisense]], a startup co-founded by Prof. Daniel Cremers, as a PhD Student and Senior Computer Vision & AI Researcher. | |
| |
| |
==== Brief Bio ==== | ==== Brief Bio ==== |
I received my Bachelor's degree (2011) in Automation from Xi'an Jiaotong University, and my Master's degree (2014) in Electrical Engineering and Information Technology from the Technical University of Munich. | I received my Bachelor's degree (2011) in Automation from Xi'an Jiaotong University, and my Master's degree (2014) in Electrical Engineering and Information Technology from the Technical University of Munich. |
From 2014 to 2016 I worked as a computer vision algorithm developer for advanced driver assistance systems (ADAS) at Continental. Since March 2016 I am a PhD student in the Computer Vision Group at the Technical University of Munich, headed by Professor Daniel Cremers. In 2018 I joined [[https://www.artisense.ai/|Artisense]], a startup co-founded by Professor Cremers, as a PhD student and senior computer vision & AI researcher. My research interests include visual SLAM and visual 3D reconstruction, as well as their combinations with semantic information. I am planning to finish my PhD in 2020. | From 2014 to 2016 I worked as a computer vision algorithm developer for advanced driver assistance systems (ADAS) at Continental. Since March 2016 I am a PhD student in the Computer Vision Group at the Technical University of Munich, headed by Professor Daniel Cremers. In 2018 I joined [[https://www.artisense.ai/|Artisense]], a startup co-founded by Professor Cremers, as a PhD student and senior computer vision & AI researcher. My research interests include visual SLAM and visual 3D reconstruction, as well as their combinations with semantic information. |
| |
Find me on [[https://scholar.google.de/citations?user=buN3yw8AAAAJ&hl=en|Google Scholar]], | Find me on [[https://scholar.google.de/citations?user=buN3yw8AAAAJ&hl=en|Google Scholar]], |
[[https://www.linkedin.com/in/rui-wang-5367398a|LinkedIn]], [[https://www.strava.com/athletes/22551758|Strava]]. | [[https://www.linkedin.com/in/rui-wang-5367398a|LinkedIn]], [[https://www.strava.com/athletes/22551758|Strava]] (highly research related). |
| |
==== Research Interests ==== | ==== Research Interests ==== |
| |
=== Semantic VO / SLAM === | == VO and vSLAM == |
| |
* ** Direct Shape ** This video shows the basic idea and some results of our paper "DirectShape: Photometric Alignment of Shape Priors for Visual Vehicle Pose and Shape Estimation". In this work, we estimate the 3D poses and shapes of cars based on a single stereo image pair. ** Note that the point clouds in the video are only for visualization purpose, they are not used in our method. ** For more details please refer to the paper [[https://arxiv.org/abs/1904.10097|arXiv]] and the [[https://vision.in.tum.de/research/vslam/direct-shape|project page]] | |
<html><center><iframe width="640" height="360" src="https://www.youtube.com/embed/QqP6zdx5OKw" frameborder="0" allowfullscreen></iframe></center></html> | |
<html><br /></html> | |
| |
=== Classic VO / SLAM === | |
| |
* ** Stereo DSO ** This video shows some results of our paper "Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras" accepted by ICCV 2017. ([[https://vision.in.tum.de/research/vslam/stereo-dso|Project Page]]) | * ** Stereo DSO ** This video shows some results of our paper "Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras" accepted by ICCV 2017. ([[https://vision.in.tum.de/research/vslam/stereo-dso|Project Page]]) |
<html><br /></html> | <html><br /></html> |
| |
=== Deep Learning Boosted VO / SLAM === | == Large-scale Relocalization == |
| |
* ** Deep Virtual Stereo Odometry (DVSO) ** In this project we design a novel deep network and train it in a semi-supervised way to predict depth map from single image, and integrate the depth map into DSO as virtual stereo measurement. Being a monocular VO approach, DVSO achieves comparable performance to the state-of-the-art stereo methods. ([[https://vision.in.tum.de/research/vslam/dvso|Project Page]]) | * ** DH3D ** "DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization" (ECCV 2020, spotlight). Please visit the [[https://vision.in.tum.de/research/vslam/dh3d|Project Page]] for code and related materials. (The video is with audio.) |
| <html><center><iframe width="640" height="360" src="https://www.youtube.com/embed/ZxZiwZugG14" frameborder="0" allowfullscreen></iframe></center></html> |
| |
| == Bring Semantic Information into vSLAM == |
| |
| * ** DirectShape ** This video shows the basic idea and some results of our paper "DirectShape: Photometric Alignment of Shape Priors for Visual Vehicle Pose and Shape Estimation". In this work, we estimate the 3D poses and shapes of cars based on a single stereo image pair. ** Note that the point clouds in the video are only for visualization purpose, they are not used in our method. ** For more details please refer to the [[https://vision.in.tum.de/research/vslam/direct-shape|Project Page]]. |
| <html><center><iframe width="640" height="360" src="https://www.youtube.com/embed/QqP6zdx5OKw" frameborder="0" allowfullscreen></iframe></center></html> |
| <html><br /></html> |
| |
| == Robustify VO with Deep Learning == |
| |
| * ** DVSO: Deep Virtual Stereo Odometry ** In this project we design a novel deep network and train it in a semi-supervised way to predict depth map from single image, and integrate the depth map into DSO as virtual stereo measurement. Being a monocular VO approach, DVSO achieves comparable performance to the state-of-the-art stereo methods. ([[https://vision.in.tum.de/research/vslam/dvso|Project Page]]) |
<html><center><iframe width="640" height="360" | <html><center><iframe width="640" height="360" |
src="https://www.youtube.com/embed/sLZOeC9z_tw" frameborder="0" allowfullscreen></iframe> | src="https://www.youtube.com/embed/sLZOeC9z_tw" frameborder="0" allowfullscreen></iframe> |
<html><br /></html> | <html><br /></html> |
| |
=== Camera Calibration === | * ** D3VO: Deep Depth, Pose and Uncertainty ** for Monocular Visual Odometry. In addition to integrate the depth maps generated by a network into DSO, like was done in DVSO, in this work we further learn to predict camera poses and uncertainty maps and fuse them into DSO. For details please visit the [[https://vision.in.tum.de/research/vslam/d3vo|Project Page]]. |
| |
| == Camera Calibration == |
| |
* ** Online Photometric Calibration ** We've conducted a project to achieve online photometric calibration, where the exposure times of consecutive frames, the camera response function, and the camera vignetting factors can be recovered in real-time. Experiments show that our estimations converge to the ground truth after only a few seconds. Our approach can be used either offline for calibrating existing datasets, or online in combination with state-of-the-art direct visual odometry or SLAM pipelines. For more details please check our paper "Online Photometric Calibration of Auto Exposure Video for Realtime Visual Odometry and SLAM". ([[https://vision.in.tum.de/research/vslam/photometric-calibration|Project Page]]) | * ** Online Photometric Calibration ** We've conducted a project to achieve online photometric calibration, where the exposure times of consecutive frames, the camera response function, and the camera vignetting factors can be recovered in real-time. Experiments show that our estimations converge to the ground truth after only a few seconds. Our approach can be used either offline for calibrating existing datasets, or online in combination with state-of-the-art direct visual odometry or SLAM pipelines. For more details please check our paper "Online Photometric Calibration of Auto Exposure Video for Realtime Visual Odometry and SLAM". ([[https://vision.in.tum.de/research/vslam/photometric-calibration|Project Page]]) |
<html><br /></html> | <html><br /></html> |
| |
==== Master Theses / IDP / Guided Research ==== | |
Please send me your transcripts and CV by email. | |
| |
==== Teaching ==== | ==== Teaching ==== |
| |
==== Service ==== | ==== Service ==== |
* Conference reviewer: CVPR, ICCV, ICRA, IROS | * Conference reviewer: CVPR, ICCV, ECCV, ICRA, IROS, AAAI |
* Journal reviewer: RA-L, T-RO | * Journal reviewer: RA-L, T-RO, AURO, TMM, P&RS |
| * Organizer: ECCV 2020 Workshop on [[https://sites.google.com/view/mlad-eccv2020|Map-based Localization for Autonomous Driving]] |
| |
==== Publications ==== | ==== Publications ==== |