DeMoN: Depth and Motion Network for Learning Monocular Stereo
ثبت نشده
چکیده
Our network is a chain of encoder-decoder networks. Figures 15 and 16 explain the details of the two encoderdecoders used in the bootstrap and iterative net part. Fig. 17 gives implementation details for the refinement net. The encoder-decoders for the bootstrap and iterative net use additional inputs which come from previous predictions. Some of these inputs, like warped images or depth from optical flow, need to be generated with special layers, which we describe here.
منابع مشابه
DeMoN: Depth and Motion Network for Learning Monocular Stereo
Our network is a chain of encoder-decoder networks. Figures 12 and 13 explain the details of the two encoderdecoders used in the bootstrap and iterative net part. Fig. 14 gives implementation details for the refinement net. The encoder-decoders for the bootstrap and iterative net use additional inputs which come from previous predictions. Some of these inputs, like warped images or depth from o...
متن کاملDeMoN: Depth and Motion Network for Learning Monocular Stereo
Our network is a chain of encoder-decoder networks. Figures 15 and 16 explain the details of the two encoderdecoders used in the bootstrap and iterative net part. Fig. 17 gives implementation details for the refinement net. The encoder-decoders for the bootstrap and iterative net use additional inputs which come from previous predictions. Some of these inputs, like warped images or depth from o...
متن کاملOn the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach
We revisit the problem of visual depth estimation in the context of autonomous vehicles. Despite the progress on monocular depth estimation in recent years, we show that the gap between monocular and stereo depth accuracy remains large—a particularly relevant result due to the prevalent reliance upon monocular cameras by vehicles that are expected to be self-driving. We argue that the challenge...
متن کاملA Machine Learning Approach to Recovery of Scene Geometry from Images
Recovering the 3D structure of the scene from images yields useful information for tasks such as shape and scene recognition, object detection, or motion planning and object grasping in robotics. In this thesis, we introduce a general machine learning approach called unsupervised CRF learning based on maximizing the conditional likelihood. We describe the application of our machine learning app...
متن کاملFusion of stereo and still monocular depth estimates in a self-supervised learning context
We study how autonomous robots can learn by themselves to improve their depth estimation capability. In particular, we investigate a self-supervised learning setup in which stereo vision depth estimates serve as targets for a convolutional neural network (CNN) that transforms a single still image to a dense depth map. After training, the stereo and mono estimates are fused with a novel fusion m...
متن کامل