カメラ内部パラメータと時空間制約を統合した教師なし単眼深度学習
Unsupervised Monocular Depth Learning with Integrated Intrinsics and Spatio-Temporal Constraints
単眼画像列からスケール付き深度・自己運動・カメラ内部パラメータを単一ネットワークで教師なし学習する手法を提案し、KITTIで高い性能と短い学習時間を示した。
著者: Kenny Chen, Alexandra Pogue, Brett T. Lopez, Ali-akbar Agha-mohammadi, Ankur Mehta
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
Monocular depth inference has gained tremendous attention from researchers in recent years and remains as a promising replacement for expensive time-of-flight sensors, but issues with scale acquisition and implementation overhead still plague these systems. To this end, this work presents an unsupervised learning framework that is able to predict at-scale depth maps and egomotion, in addition to camera intrinsics, from a sequence of monocular images via a single network. Our method incorporates both spatial and temporal geometric constraints to resolve depth and pose scale factors, which are enforced within the supervisory reconstruction loss functions at training time. Only unlabeled stereo sequences are required for training the weights of our single-network architecture, which reduces overall implementation overhead as compared to previous methods. Our results demonstrate strong performance when compared to the current state-of-the-art on multiple sequences of the KITTI driving dataset and can provide faster training times with its reduced network complexity.
