Abstract
Leveraging masked autoencoders, we achieve 4 times classification accuracy than that of Vision Transformers, and 2 times better classification accuracy than Convolutional Neural Networks on 50% masked LiDAR images acquired with sparse photon detections.
© 2023 The Author(s)
PDF ArticleMore Like This
Wen-Chih Liu, Jayanth Pratap, Abhiram R. Bhashyam, Neal C. Chen, Quanzheng Li, and Xiang Li
HTh2C.1 Digital Holography and Three-Dimensional Imaging (DH) 2023
Lili Li, Santosh Kumar, and Yuping Huang
FM1B.3 Frontiers in Optics (FiO) 2023
Zipei Zheng, Yong Meng Sua, Shenyu Zhu, Patrick Rehain, and Yuping Huang
JM4A.88 Frontiers in Optics (FiO) 2023