Dense monocular reconstruction using surface normals

This paper presents an efficient framework for dense 3D scene reconstruction using input from a moving monocular camera. Visual SLAM (Simultaneous Localisation and Mapping) approaches based solely on geometric methods have proven to be quite capable of accurately tracking the pose of a moving camera and simultaneously building a map of the environment in real-time. However, most of them suffer from the 3D map being too sparse for practical use. The missing points in the generated map correspond mainly to areas lacking texture in the input images, and dense mapping systems often rely on hand-crafted priors like piecewise-planarity or piecewise-smooth depth. These priors do not always provide the required level of scene understanding to accurately fill the map. On the other hand, Convolutional Neural Networks (CNNs) have had great success in extracting high-level information from images and regressing pixel-wise surface normals, semantics, and even depth. In this work we leverage this high-level scene context learned by a deep CNN in the form of a surface normal prior. We show, in particular, that using the surface normal prior leads to better reconstructions than the weaker smoothness prior.

Authors

• Chamara Saroj Weerasekera
• Yasir Latif
• Ravi Garg
• Ian D. Reid 0001

Keywords

• Surface reconstruction
• Cameras
• Image reconstruction
• Three-dimensional displays
• Neural networks
• Simultaneous localization and mapping
• Robot vision systems
• Monocular
• Surface Normals
• Dense Reconstruction
• Neural Network
• Convolutional Neural Network
• Density Map
• Deep Convolutional Neural Network
• Tracking Accuracy
• Environment Map
• 3D Density
• Energy Minimization
• Convolutional Layers
• Exhaustive Search
• Regularization Term
• Test Sequences
• Depth Map
• Images In Set
• Image Edge
• Cost Volume
• Depth Prediction
• Multi-scale Convolutional Neural Network
• Smoothness Regularization
• Camera Pose
• Depth Estimation
• Dual Variables
• Scene Details
• Surface Orientation
• Pixel Location