With no less than four accepted papers, the DFKI research area Augmented Vision was represented at the ICCV 2023 conference from October 2 to 6 in Paris, France.
The 4 accepted papers are:
- U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds
Yan Di, Chenyangguang Zhang, Ruida Zhang, Fabian Manhardt, Yongzhi Su, Jason Raphael Rambach, Didier Stricker, Xiangyang Ji, Federico Tombari
- FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision.
Khurram Azeem Hashmi, Goutham Kallempudi, Didier Stricker, Muhammad Zeshan Afzal
- Introducing Language Guidance in Prompt-based Continual Learning
Muhammad Gulzain Ali Khan, Muhammad Ferjad Naeem; Luc Van Gool; Federico Tombari; Didier Stricker, Muhammad Zeshan Afzal
- DELO: Deep Evidential LiDAR Odometry using Partial Optimal Transport
Sk Aziz Ali, Djamila Aouada, Gerd Reis, Didier Stricker
In addition, the scientists from the research area won no less than three first prizes at the conference.
DFKI's VPraveen Nathan, Sandeep Inuganti, Yongzhi Su and Jason Rambach, all from the Augmented Vision research department, won three first-place awards in the prestigious 2023 BOP Object Pose Estimation Challenge in the categories of
- Overall Best RGB Method,
- Overall Best Segmentation Method and
- The Best BlenderProc-Trained Segmentation Method.
The BOP benchmark and challenge address the problem of 6-degree-of-freedom object pose estimation, which is of great importance for many applications such as robot grasping or augmented reality.
The awards were accepted by Yongzhi Su and Dr. Jason Rambach on behalf of the DFKI team and were followed by a short presentation of the method. The award-winning method was based on the CVPR 2022 paper "ZebraPose".
The winning approach was developed by a team led by DFKI's Augmented Vision research unit, which also included researchers from Zhejiang University.
Website of the ICCV