Towards Comprehensive Representation Enhancement in Semantics-guided Self-supervised Monocular Depth Estimation

no code implementations • ECCV 2022 • Jingyuan Ma, Xiangyu Lei, Nan Liu, Xian Zhao, ShiLiang Pu

Semantics-guided self-supervised monocular depth estimation has been widely researched, owing to the strong cross-task correlation of depth and semantics.

Metric Learning Monocular Depth Estimation +2

Vehicle Pose and Shape Estimation through Multiple Monocular Vision

1 code implementation • 10 Feb 2018 • Wenhao Ding, Shuaijun Li, Guilin Zhang, Xiangyu Lei, Huihuan Qian

We utilize state-of-the-art convolutional neural networks (CNNs) to extract vehicles' semantic keypoints and introduce a Cross Projection Optimization (CPO) method to estimate the 3D pose.