Dense multi-planar scene estimation from a sparse set of images

Ego-motion estimation and 3D scene reconstruction from image data has been a long term aim both in the Robotics and Computer Vision communities. Nevertheless, while both visual SLAM and Structure from Motion already provide an accurate ego-motion estimation, visual scene estimation does not offer yet such a satisfactory result; being in most cases limited to a sparse set of salient points. In this paper we propose an algorithm to densify a sparse point-based reconstruction into a dense multi-plane based one, from the only input of a set of sparse images.

Authors

• Alberto Argiles
• Javier Civera 0001
• Luis Montesano

Keywords

• Three dimensional displays
• Cameras
• Image reconstruction
• Estimation
• Feature extraction
• Visualization
• Silicon
• Sparse Set Of Images
• 3D Reconstruction
• Point Cloud
• Geometric Constraints
• 3D Scene
• Structure From Motion
• Simultaneous Localization And Mapping
• Salient Points
• Computer Vision Community
• Sparse Reconstruction
• Sparse Imaging
• Number Of Planes
• Image Pairs
• Robust Algorithm
• Overview Of Methods
• Image Point
• 3D Point
• Internal Calibration
• 3D Point Cloud
• Motion Estimation
• Dense Reconstruction
• Sparse Point
• Homography
• Bundle Adjustment
• Projection Point
• Fundamental Matrix
• Multi-view Stereo
• Camera Motion
• Texture Areas
• Building Facades