Both sides previous revision
Previous revision
Next revision
|
Previous revision
|
members:yangn [2019/09/09 16:41] yangn |
members:yangn [2022/03/28 06:48] (current) yangn |
</member> | </member> |
| |
==== News ==== | <html><center><a href="https://nan-yang.me/" target="_blank"><h2 style="color:blue;text-decoration: underline;">>>Personal Website<<</h2></a></center></html> |
* [09.2019] One paper accepted for CoRL 2019, Osaka. | * [12.2021] [[https://vision.in.tum.de/research/vslam/tandem|TANDEM]] won the [[https://3dv2021.surrey.ac.uk/prizes/|Best Demo Award]] at //3DV 2021//! |
* [07.2018] One paper accepted for ECCV 2018, Munich -- ** oral ** (2.5%, [[https://youtu.be/2_nDLpGtY1Y|link]]). | * [09.2021] [[https://vision.in.tum.de/research/vslam/tandem|TANDEM]] accepted at //CoRL// 2021. Check out the [[https://arxiv.org/abs/2111.07418|paper]] and [[https://github.com/tum-vision/tandem|code]]. |
* [06.2018] One paper accepted for IROS 2018, Madrid. | * [06.2021] [[https://vision.in.tum.de/research/monorec|MonoRec]](CVPR 21') code released on [[https://github.com/Brummi/MonoRec|Github]]. |
* [05.2018] One paper accepted for publication in RA-L. | * [05.2021] Received //Outstanding Reviewer// for [[http://cvpr2021.thecvf.com/node/184|CVPR 2021]]. |
| * [04.2021] [[https://www.4seasons-dataset.com/|4Seasons]] dataset is now public. |
| * [12.2020] Finished the internship at Facebook Reality Labs where I worked on collaborative mapping. |
| * [10.2020] [[https://vision.in.tum.de/research/vslam/lm-reloc|LM-Reloc]] accepted at //3DV// 2020. |
| * [09.2020] Started the internship at //Facebook Reality Labs//. |
| * [05.2020] Co-organized [[https://sites.google.com/view/mlad-eccv2020|Map-based Localization for Autonomous Driving Workshop]], //ECCV// 2020. |
| * [02.2020] [[https://vision.in.tum.de/research/vslam/d3vo|D3VO]] accepted as an oral presentation at //CVPR// 2020. |
| |
==== Research Interests ==== | ===== Brief Bio ===== |
My research interests lie in incorporating deep learning into visual odometry and SLAM. | Find me on [[https://scholar.google.de/citations?user=pUj2ffwAAAAJ&hl=en|Google Scholar]], [[https://www.linkedin.com/in/nan-yang-089aa8aa/|Linkedin]], [[https://twitter.com/NanYang719|Twitter]]. |
| |
** Deep Virtual Stereo Odometry (DVSO)** -- [[:research:vslam:dvso|Project Page]] | I received my Bachelor's degree in Computer Science from Beijing University of Posts and Telecommunications and my Master's degree in Informatics from the Technical University of Munich. Since May 2018, I am a Ph.D. student and senior computer vision researcher in [[https://www.artisense.ai/|Artisense]], a startup co-founded by [[:members:cremers|Prof. Daniel Cremers]]. From September 2020 until December 2020, I was an intern in Facebook Reality Labs working on collaborative mapping. |
| |
| ===== Research ===== |
| My research interest lies in enhancing classical 3D vision, e.g., visual odometry / simultaneously localization and mapping (SLAM), re-localization, and dense reconstruction, with the aid of deep neural networks. Here are some selected projects: |
| |
| ==== Visual Odometry ==== |
| * **Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry**, //ECCV// 2018, Oral Presentation. |
<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> |
| </center></html> |
| <html><br /></html> |
| * **D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry**, //CVPR// 2020, Oral Presentation. |
| <html><center><iframe width="640" height="360" |
| src="https://www.youtube.com/embed/a7CAkJbhcm8" frameborder="0" allowfullscreen></iframe> |
| </center></html> |
| <html><br /></html> |
| * **Multi-Frame GAN: Image Enhancement for Stereo Visual Odometry in Low Light |
| **, //CoRL// 2019, Long Oral Presentation. |
| <html><center><iframe width="640" height="360" |
| src="https://www.youtube.com/embed/OdYkFuZv204" frameborder="0" allowfullscreen></iframe> |
| </center></html> |
| <html><br /></html> |
| |
| ==== Dense Reconstruction ==== |
| * **MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera**, //CVPR// 2021. |
| <html><center><iframe width="640" height="360" |
| src="https://www.youtube.com/embed/-gDSBIm0vgk" frameborder="0" allowfullscreen></iframe> |
| </center></html> |
| <html><br /></html> |
| * *TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo*, //CoRL// 2021, **<fc #ff0000>Best Demo Award</fc>** at //3DV// 2021. |
| <html><center><iframe width="640" height="360" |
| src="https://www.youtube.com/embed/L4C8Q6Gvl1w" frameborder="0" allowfullscreen></iframe> |
| </center></html> |
| <html><br /></html> |
| |
| ==== Re-localization ==== |
| * **LM-Reloc: Levenberg-Marquardt Based Direct Visual Relocalization**, //3DV// 2020. |
| <html><center><iframe width="640" height="360" |
| src="https://www.youtube.com/embed/i7TyTwKD734" frameborder="0" allowfullscreen></iframe> |
| </center></html> |
| <html><br /></html> |
| |
| ==== Object-level Perceptions ==== |
| * **DirectShape: Photometric Alignment of Shape Priors for Visual Vehicle Pose and Shape Estimation**, //ICRA// 2020. |
| <html><center><iframe width="640" height="360" |
| src="https://www.youtube.com/embed/QqP6zdx5OKw" frameborder="0" allowfullscreen></iframe> |
| </center></html> |
| <html><br /></html> |
| |
| * **Learning Monocular 3D Vehicle Detection without 3D Bounding Box Labels**, //GCPR// 2020. |
| <html><center><iframe width="640" height="360" |
| src="https://www.youtube.com/embed/Qxj0-jASHUg" frameborder="0" allowfullscreen></iframe> |
</center></html> | </center></html> |
<html><br /></html> | <html><br /></html> |
| |
==== Brief Bio ==== | ==== Professional Services ==== |
Nan Yang received his Bachelor's degree in Computer Science from Beijing University of Posts and Telecommunications and his Master's degree in Informatics from the Technical University of Munich. Since May 2018, he is a PhD student and senior computer vision & AI researcher in [[https://www.artisense.ai/|Artisense]], a startup co-founded by [[:members:cremers|Prof. Daniel Cremers]]. | * Journal reviewer: RA-L, AURO, ISPRS |
| * Conference reviewer: CVPR, ECCV, ICCV, ICLR, AAAI, ICRA, IROS |
| * Co-organized Map-based Localization for Autonomous Driving Workshop, [[https://sites.google.com/view/mlad-eccv2020|ECCV 2020]] and [[https://sites.google.com/view/mlad-iccv2021|ICCV 2021]]. |
| |
==== Publications ==== | ==== Publications ==== |