Fig 8 - uploaded by Kwan-Yee Kenneth Wong
Content may be subject to copyright.
Source publication
This paper presents a novel technique for reconstructing an outdoor sculpture from an uncalibrated image sequence acquired around it using a hand-held camera. The technique introduced here uses only the silhouettes of the sculpture for both motion estimation and model reconstruction, and no corner detection nor matching is necessary. This is very i...
Context in source publication
Context 1
... the whole sequence was then rectified so that all the images of the string in the rectified sequence became coincident (see Fig. 7). The circular motion estimation algorithm was then applied to this rectified sequence, followed by the iterative refinement process. The final camera configuration estimated from the rectified sequence is shown in Fig. 8. Using the estimated motion, an octree representation of the horse was built using a space carving algorithm (see Fig. 10) and a surface representation was then extracted using the marching cubes algorithm. Figure 11 shows different novel views of the reconstructed sculpture model with texture-mapping, and Fig. 9 shows the underlying ...
Similar publications
In this paper, we present a large-scale detailed 3D face dataset, FaceScape, and the corresponding benchmark to evaluate single-view facial 3D reconstruction. By training on FaceScape data, a novel algorithm is proposed to predict elaborate riggable 3D face models from a single image input. FaceScape dataset provides 18,760 textured 3D faces, captu...
Citations
Profiles of a sculpture provide rich information about its geometry, and can be used for shape recovery under known camera motion. By exploiting correspondences induced by epipolar tangents on the profiles, a successful solution to motion estimation from profiles has been developed in the special case of circular motion. The main drawbacks of using circular motion alone, namely the difficulty in adding new views and part of the object always being invisible, can be overcome by incorporating arbitrary general views of the object and registering its new profiles with the set of profiles resulted from the circular motion. In this paper, we describe a complete and practical system for producing a three-dimensional (3-D) model from uncalibrated images of an arbitrary object using its profiles alone. Experimental results on various objects are presented, demonstrating the quality of the reconstructions using the estimated motion.
