GroundNet: Monocular Ground Plane Normal Estimation with Geometric Consistency
arXiv:1811.07222
Abstract
We focus on estimating the 3D orientation of the ground plane from a single image. We formulate the problem as an inter-mingled multi-task prediction problem by jointly optimizing for pixel-wise surface normal direction, ground plane segmentation, and depth estimates. Specifically, our proposed model, GroundNet, first estimates the depth and surface normal in two separate streams, from which two ground plane normals are then computed deterministically. To leverage the geometric correlation between depth and normal, we propose to add a consistency loss on top of the computed ground plane normals. In addition, a ground segmentation stream is used to isolate the ground regions so that we can selectively back-propagate parameter updates through only the ground regions in the image. Our method achieves the top-ranked performance on ground plane normal estimation and horizon line detection on the real-world outdoor datasets of ApolloScape and KITTI, improving the performance of previous art by up to 17.7% relatively.
arXiv commentCamera Ready for ACM MM 2019
References in corpus (8)
- Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency
- Deep Reinforcement Learning for Autonomous Driving
- Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors
- Geometry-Aware Recurrent Neural Networks for Active Visual Recognition
- Visual Compiler: Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator
- CyLKs: Unsupervised Cycle Lucas-Kanade Network for Landmark Tracking
- Image Labeling with Markov Random Fields and Conditional Random Fields