Summary: IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, VOL. 4, NO. 4, OCTOBER-DECEMBER 1998 293
Novel View Synthesis by
Cascading Trilinear Tensors
Shai Avidan and Amnon Shashua, Member, IEEE
Abstract--We present a new method for synthesizing novel views of a 3D scene from two or three reference images in full
correspondence. The core of this work is the use and manipulation of an algebraic entity termed the trilinear tensor that links point
correspondences across three images. For a given virtual camera position and orientation, a new trilinear tensor can be computed
based on the original tensor of the reference images. The desired view can then be created using this new trilinear tensor and point
correspondences across two of the reference images.
Index Terms--Image-based rendering, trilinear tensor, virtual reality, image manipulation.
-------------------- F --------------------
HIS paper addresses the problem of synthesizing a
novel image from an arbitrary viewing position given
two or three reference images (registered by means of an
optic-flow engine) of the 3D scene.
The most significant aspect of our approach is the ability
to synthesize images that are far away from the viewing
positions of the sample reference images without ever ex-
plicitly computing any 3D information about the scene.