Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
members:wangr [2020/03/09 21:59] Rui Wang |
members:wangr [2021/12/26 16:34] Rui Wang |
||
---|---|---|---|
Line 1: | Line 1: | ||
{{page> | {{page> | ||
+ | |||
+ | |||
+ | |||
+ | This is my old webpage which is not maintained since March 2021. ** [[https:// | ||
+ | |||
==== News ==== | ==== News ==== | ||
- | * [02.2020] D3VO is accepted by CVPR 2020. Camera ready version coming soon. ([[https:// | + | |
+ | * [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" | ||
+ | * [05.2020] We are organizing a workshop together with a challenge on [[https:// | ||
+ | * [05.2020] The results of Stereo DSO on KITTI Odometry test set are uploaded to the [[https:// | ||
+ | | ||
* [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:// | * [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:// | ||
* [10.2018] The code for LDSO (Direct Sparse Odometry with Loop Closure) has been released! ([[https:// | * [10.2018] The code for LDSO (Direct Sparse Odometry with Loop Closure) has been released! ([[https:// | ||
Line 12: | Line 22: | ||
==== Brief Bio ==== | ==== Brief Bio ==== | ||
I received my Bachelor' | I received my Bachelor' | ||
- | 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:// | + | 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:// |
Find me on [[https:// | Find me on [[https:// | ||
Line 19: | Line 29: | ||
==== Research Interests ==== | ==== Research Interests ==== | ||
- | === Semantic | + | == VO and vSLAM == |
- | + | ||
- | * ** DirectShape ** This video shows the basic idea and some results of our paper " | + | |
- | < | + | |
- | < | + | |
- | + | ||
- | === Classic VO / SLAM === | + | |
* ** Stereo DSO ** This video shows some results of our paper " | * ** Stereo DSO ** This video shows some results of our paper " | ||
Line 41: | Line 45: | ||
< | < | ||
- | === VO / SLAM with Deep Learning | + | == Large-scale Relocalization |
+ | |||
+ | * ** DH3D ** "DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization" | ||
+ | < | ||
+ | |||
+ | == Bring Semantic Information into vSLAM == | ||
+ | |||
+ | * ** DirectShape ** This video shows the basic idea and some results of our paper " | ||
+ | < | ||
+ | < | ||
+ | |||
+ | == 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:// | * ** 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:// | ||
Line 49: | Line 64: | ||
< | < | ||
- | === 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:// |
+ | |||
+ | == Camera Calibration == | ||
* ** Online Photometric Calibration ** We've conducted a project to achieve online photometric calibration, | * ** Online Photometric Calibration ** We've conducted a project to achieve online photometric calibration, | ||
Line 55: | Line 72: | ||
< | < | ||
- | ==== Master Theses / IDP / Guided Research ==== | ||
- | Please send me your transcripts and CV by email. | ||
==== Teaching ==== | ==== Teaching ==== | ||
Line 66: | Line 81: | ||
==== Service ==== | ==== Service ==== | ||
* Conference reviewer: CVPR, ICCV, ECCV, ICRA, IROS, AAAI | * Conference reviewer: CVPR, ICCV, ECCV, ICRA, IROS, AAAI | ||
- | * Journal reviewer: RA-L, T-RO, AURO | + | * Journal reviewer: RA-L, T-RO, AURO, TMM, P&RS |
+ | * Organizer: ECCV 2020 Workshop on [[https:// | ||
==== Publications ==== | ==== Publications ==== |