Modeling and rendering architecture from photographs: a hybrid geometry- and image-based approach
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Least-squares 3D reconstruction from one or more views and geometric clues
Computer Vision and Image Understanding
FlexiStickers: photogrammetric texture mapping using casual images
ACM SIGGRAPH 2009 papers
Least-squares 3D reconstruction from one or more views and geometric clues
Computer Vision and Image Understanding
Scene modelling from sparse 3D data
Image and Vision Computing
The mapping of texture on VR polygonal models
3DIM'99 Proceedings of the 2nd international conference on 3-D digital imaging and modeling
PALM: portable sensor-augmented vision system for large-scene modeling
3DIM'99 Proceedings of the 2nd international conference on 3-D digital imaging and modeling
Hi-index | 0.00 |
We present an approach for creating realistic synthetic views of existing architectural scenes from a sparse set of still photographs. Our approach, which combines both geometry-based and image-based modeling and rendering techniques, has two components. The first component is an easy-to-use photogrammetric modeling system which facilitates the recovery of a basic geometric model of the photographed scene. The modeling system is effective and robust because it exploits the constraints that are characteristic of architectural scenes. The second component is a {\em model-based} stereo algorithm, which recovers precisely how the real scene deviates from the basic model. Guided by the basic model, our stereo approach can robustly recover accurate depth from image pairs with large baselines with respect to the objects in the scene. Consequently, our approach can model large architectural environments with far fewer photographs than current image-based modeling approaches. As an intermediate result, we present {\em view-dependent texture mapping}, a method of better simulating geometric detail on basic models. Our approach can recover models for use in either geometry-based or image-based rendering systems. We present results that demonstrate our approach''s abilty to create realistic renderings of architectural scenes from viewpoints far from the original photographs.