SS07: Towards Realistic 3D Deep Learning with Limited Supervision
Motivation & significance
•Aims to bring together researchers and practitioners to explore the latest theoretical advancements, cutting-edge techniques, and practical applications of 3D deep learning under limited supervision. We welcome contributions that address fundamental research challenges, propose innovative solutions, or showcase real-world applications, with a focus on overcoming data scarcity while ensuring robustness and scalability.
Topics of interest
•3D reconstruction from sparse observations
•Generative model-assisted 3D reconstruction and novel view synthesis
•Semi-supervised and weakly-supervised learning for 3D data
•Self-supervised learning for 3D representation learning
•2D model-assisted 3D deep learning
•Domain adaptation and generalization for 3D models in real-world environments
•Leveraging unlabeled or sparse data for 3D scene understanding
•Applications of limited supervision in real-world 3D tasks (e.g., AR/VR, robotics, medical imaging, multimedia)
•Challenges in evaluating and benchmarking 3D deep learning models under limited supervision
Organizers
Xun Xu, Institute for Infocomm Research (I2R), A*STAR, email: Xu_Xun@i2r.a-star.edu.sg
Shijie Li, Institute for Infocomm Research (I2R), A*STAR, email: li_shijie@i2r.a-star.edu.sg
Hao Su, University of California San Diego, USA, email: haosu@eng.ucsd.edu
Xiatian Zhu, University of Surrey, UK, email: haosu@eng.ucsd.edu
Juergen Gall, University of Bonn, email: gall@iai.uni-bonn.de
Xulei Yang, Institute for Infocomm Research (I2R), A*STAR, email: yang_xulei@i2r.a-star.edu.sg