Geo-Supervised Visual Depth Prediction
arXiv:1807.11130
Abstract
We propose using global orientation from inertial measurements, and the bias it induces on the shape of objects populating the scene, to inform visual 3D reconstruction. We test the effect of using the resulting prior in depth prediction from a single image, where the normal vectors to surfaces of objects of certain classes tend to align with gravity or be orthogonal to it. Adding such a prior to baseline methods for monocular depth prediction yields improvements beyond the state-of-the-art and illustrates the power of gravity as a supervisory signal.
arXiv commentICRA 2019, RA-L 2019
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
- Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
- Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation
- Inverse Compositional Spatial Transformer Networks