Monocular depth estimation - Open Access .click

Neural Processing Letters, 2021
Monocular depth estimation (MDE), which is the task of using a single image to predict scene depths, has gained considerable interest, in large part owing to the popularity of applying deep learning methods to solve “computer vision problems”. Monocular cues provide sufficient data for humans to instantaneously extract an understanding of scene ...
Janice Pan, Alan C. Bovik
openaire +2 more sources

Fast Monocular Depth Estimation on an FPGA

2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2020
Depth sensing is crucial for understanding 3D scenes on embedded systems such as home robots, self-driving cars, and drones. Monocular depth estimation which gives pixel-wise depth from a general camera, has attracted attention in recent years, due to the reliability, low-cost and small area requirement.
Youki Sada +5 more
openaire +1 more source

Geometric Pretraining for Monocular Depth Estimation

2020 IEEE International Conference on Robotics and Automation (ICRA), 2020
ImageNet-pretrained networks have been widely used in transfer learning for monocular depth estimation. These pretrained networks are trained with classification losses for which only semantic information is exploited while spatial information is ignored. However, both semantic and spatial information is important for per-pixel depth estimation.
Kaixuan Wang +4 more
openaire +1 more source

deep learning
depth estimation
self-supervised learning

transformer
computer vision
technology

cnn