Abstract | ||
---|---|---|
We present a novel approach to 3D reconstruction which is inspired by the human visual system. This system unifies standard appearance matching and triangulation techniques with higher level reasoning and scene understanding, in order to resolve ambiguities between different interpretations of the scene. The types of reasoning integrated in the approach includes recognising common configurations of surface normals and semantic edges (e.g. convex, concave and occlusion boundaries). We also recognise the coplanar, collinear and symmetric structures which are especially common in man made environments. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ICCV.2015.96 | ICCV |
Keywords | Field | DocType |
high level scene cues,stereo reconstruction,3D reconstruction,human visual system,standard appearance matching,triangulation techniques,higher level reasoning,scene understanding,scene interpretations,surface normals,semantic edges,common configuration recognition,coplanar structure recognition,collinear structure recognition,symmetric structure recognition | Computer vision,Pattern recognition,Computer science,Human visual system model,Regular polygon,Triangulation (social science),Stereo reconstruction,Artificial intelligence,3D reconstruction | Conference |
Volume | Issue | ISSN |
2015 | 1 | 1550-5499 |
Citations | PageRank | References |
2 | 0.35 | 30 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simon Hadfield | 1 | 356 | 22.65 |
Richard Bowden | 2 | 1840 | 118.50 |