Epipolar Geometry and Linear Subspace Methods: A New Approach to Weak Calibration
International Journal of Computer Vision
Photorealistic Scene Reconstruction by Voxel Coloring
International Journal of Computer Vision
A Theory of Shape by Space Carving
International Journal of Computer Vision - Special issue on Genomic Signal Processing
Calibration-Free Augmented Reality
IEEE Transactions on Visualization and Computer Graphics
Affine Object Representations for Calibration-Free Augmented Reality
VRAIS '96 Proceedings of the 1996 Virtual Reality Annual International Symposium (VRAIS 96)
Physically-Valid View Synthesis by Image Interplation
VSR '95 Proceedings of the IEEE Workshop on Representation of Visual Scenes
Pose and Motion Recovery from Feature Correspondences and a Digital Terrain Map
IEEE Transactions on Pattern Analysis and Machine Intelligence
Correspondence-Free Determination of the Affine Fundamental Matrix
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robotics and Computer-Integrated Manufacturing
Robust variational segmentation of 3d objects from multiple views
DAGM'06 Proceedings of the 28th conference on Pattern Recognition
AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
Surface measures for accuracy evaluation in 3d face reconstruction
Pattern Recognition
A survey of methods for volumetric scene reconstruction from photographs
VG'01 Proceedings of the 2001 Eurographics conference on Volume Graphics
| Hi-index | 0.00 |
A technique is presented for computing 3D scene structure from point and line features in monocular image sequences. Unlike previous methods, the technique guarantees the completeness of the recovered scene, ensuring that every scene feature that is detected in each image is reconstructed. The approach relies on the presence of four or more reference features whose correspondences are known in all the images. Under an orthographic or affine camera model, the parallax of the reference features provides constraints that simplify the recovery of the rest of the visible scene. An efficient recursive algorithm is described that uses a unified framework for point and line features. The algorithm integrates the tasks of feature correspondence and structure recovery, ensuring that all reconstructible features are tracked. In addition, the algorithm is immune to outliers and feature drift, two weaknesses of existing structure from motion techniques. Experimental results are presented for real images.