Abstract | ||
---|---|---|
This paper is dedicated to the 3D reconstruction of thin tubular structures, such as cables or ropes, from a given image sequence. This is a challenging task, mainly because of self-occlusions of the structure and its thin features. We present an approach that combines image processing tools with physics simulation to faithfully reconstruct jumbled and tangled cables in 3D. Our method estimates the topology of the tubular object in the form of a single 1D path and also computes a topology-aware reconstruction of its geometry. We evaluate our method on both synthetic and real datasets and demonstrate that our method favourably compares to state-of-the-art methods. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1145/2669024.2669035 | SIGGRAPH Asia 2013 Technical Briefs |
Keywords | Field | DocType |
curve, surface, solid, and object representations,surface reconstruction,topology,tubular structures | Computer vision,Surface reconstruction,Topology,Dynamical simulation,Computer graphics (images),Computer science,Image processing,Artificial intelligence,Image sequence,3D reconstruction | Conference |
Citations | PageRank | References |
4 | 0.40 | 12 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tobias Martin | 1 | 20 | 2.78 |
Juan Montes | 2 | 4 | 0.40 |
Jean Charles Bazin | 3 | 192 | 16.87 |
Tiberiu Popa | 4 | 473 | 32.74 |