E2SRI: Learning to Super-Resolve IntensityImages from Events- Author : Mohammad Mostafavi, Yeongwoo Nam, Jonghyun Choi, and Kuk-Jin Yoon – Published Date : July 2021 – Category : Super Resolution, Event Camera – Place of publication : IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 Atstract: An event camera reports per-pixel intensity differences as an asynchronous…
Scanline Resolution-invariant Depth Completion using a Single Image and Sparse LiDAR Point Cloud- Author : Kwonyoung Ryu(KAIST), Kang-il Lee (KAIST), Jegyeong Cho (KAIST) and Kuk-Jin Yoon (KAIST) – Published Date : TBD – Category : Depth Completion – Place of publication : IEEE Robotics and Automation Letters (RA-L) 2021 Abstract: Most existing deep learning-based depth completion methods are…
EOMVS : Event-based Omnidirectional Multi-View Stereo- Author : Hoonhee Cho (KAIST), Jae-Seok Jeong (KASIT), Kuk-Jin Yoon (KAIST) – Published Date : TBD – Category : Multi-view Stereo – Place of publication : IEEE Robotics and Automation Letters (RA-L) 2021 Abstract: Event-based cameras sense changes in light intensity and asynchronously output event data. These cameras have the advantage…
We have one paper accepted to IJCAI 2021 Workshop on Artificial Intelligence for Autonomous Driving. The paper is “Evaluating Region Modification based Data Augmentation Techniques for Low Level Vision Tasks” by Pranjay Shyam, Sandeep Singh Sengar, Kuk-Jin Yoon, Kyung-Soo Kim.
Evaluating Region Modification based Data Augmentation Techniques for Low Level Vision Tasks- Author : Pranjay Shyam (KAIST), Sandeep Singh Sengar (University of Copenhagen), Kuk-Jin Yoon (KAIST) and Kyung-Soo Kim (KAIST) – Published Date : TBD – Category : Image Enhancement – Place of publication : IJCAI 2021 Workshop on Artificial Intelligence for Autonomous Driving Abstract: Region modification-based…
VILab won CVPRW 2021 DSEC competition. “EI-Stereo” by S. Mohammad Mostafavi I., Yeongwoo Nam, Kuk-Jin Yoon, and Jonghyun Choi achieves the best performance using both the event data and image (E + I). And “CESNet” by Hyeokjun Kweon, Jaeseok Jeong, Sung-hoon Yoon, Yujeong Chae, and Kuk-Jin Yoon achieves the best performance using only event data.…
We have one paper accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR) 2021. The paper is “EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation” by Lin Wang, Yujeong Chae, Sung-Hoon Yoon, Tae-Kyun Kim and Kuk-Jin Yoon. [Publication Link]
We have one paper accepted to the International Conference on Robotics and Automation(ICRA). The paper is “Adversarially trained Hierarchical Feature Extractor for Vehicle Re-identification” by Pranjay Shyam, Kuk-Jin Yoon and Kyung-Soo Kim. [Publication Link]
EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation- Author : Lin Wang, Yujeong Chae, Sung-Hoon Yoon, Tae-Kyun Kim and Kuk-Jin Yoon – Published Date : TBD – Category : Knowledge Distillation – Place of publication : IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021 Abstract: TBD
Adversarially trained Hierarchical Feature Extractor for Vehicle Re-identification- Author : Pranjay Shyam, Kuk-Jin Yoon and Kyung-Soo Kim – Published Date : TBD – Category : Vehicle Re-Identification – Place of publication : International Conference on Robotics and Automation (ICRA) 2021 Abstract: TBD