Edge-Constrained Joint View Triangulation for Image Interpolation

Maxime Lhuillier (1) , Long Quan (1)

1 MOVI - Modeling, localization, recognition and interpretation in computer vision

Image-based-interpolation creates smooth and photorealistic views between two view points. The concept of joint view triangulation (JVT) has been proven to be an efficient multi-view representation to handle visibility issue. However, the existing JVT, built only on a regular sampling grid, often produces undesirable artifacts for artificial objects. To tackle these problems, a new edge-constrained joint view triangulation is developed in this paper to integrate contour points and artificial rectilinear objects as triangulation constraints. Also a super-sampling technique is introduced to refine visible boundaries. The new algorithm is successfully demonstrated on many real image pairs.

Domaines: Synthèse d'image et réalité virtuelle [cs.GR]

Maxime Lhuillier, Long Quan. Edge-Constrained Joint View Triangulation for Image Interpolation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR '00), Jun 2000, Hilton Head Island, United States. pp.218--224, ⟨10.1109/CVPR.2000.854792⟩. ⟨inria-00590139⟩