Special Session 3
3D Vision

Submission Link: http://www.easychair.org/conferences/?conf=icvr2022
(Select Track Special Session 3: 3D Vision)

Submission deadline: April 1, 2022
(Final Call!)

With the rapid development of 3D imaging sensors, such as depth cameras and laser scanning systems, 3D data become increasingly accessible. Meanwhile, the boost of various deep learning algorithms, such as convolutional neural networks and deep reinforcement learning, further increases the usability of 3D vision systems. Driven by these factors, 3D vision becomes an emerging and core component for numerous applications, such as autonomous driving, AR/VR, and robotics.

Although remarkable progress has been achieved in this area during the last few years, there are still several challenges that need to be addressed, such as the noisy, sparse, and irregular nature of point clouds, the high cost to label 3D data, and the necessity to integrate geometry-based and learning based techniques. In addition to this, 3D data produced by different 3D imaging sensors (e.g., structured light, stereo, LiDAR, time-of-flight) have different characteristics. Therefore, it is necessary to investigate general algorithms that can mitigate the domain gap between different types of 3D data, such as point clouds, meshes or depth images.

The aim of this special session is to collect and present the latest research developments in learning-based 3D vision theories and their applications, and to inspire future research in this area.

 Topics of interest include, but are not limited to:  
– Meta-learning, weakly-supervised learning, contrastive learning, and reinforcement learning for 3D vision
– Domain adaption, generalization, and uncertainty in 3D vision
– Embodied intelligence with 3D vision
– Point cloud registration, 3D modelling, and reconstruction
– Visual, LiDAR, and multi-sensor SLAM
– 3D object detection, recognition, classification, and tracking
– Pose estimation and grasping of 3D objects
– Stereo matching, depth estimation, and neural rendering
– Semantic and instance segmentation of point clouds
– Scene flow and spatio-temporal learning from point clouds
– Feature learning in 3D point clouds
– 3D vision for X (e.g., robotics, self-driving vehicles, AR/VR)

Stefano Berretti, Associate Professor, University of Florence, Italy (Email:stefano.berretti@unifi.it)
Yulan Guo, Associate Professor, National University of Defense Technology & Sun Yat-sen University, China (Email: guoyulan@sysu.edu.cn)
Hanyun Wang, Associate Professor, Information Engineering University, China