Cheng Wan

Multiple View Geometry under Projective Projection in Space-Time

This paper introduces multiple view geometry under projective projection from four-dimensional space to two-dimensional space which can represent multiple view geometry under the projection of space-time. We show the multifocal tensors defined under space-time projective projection can be derived from non-rigid object motions viewed from multiple cameras with arbitrary translational motions, and they are practical for generating images of non-rigid object motions viewed from cameras with arbitrary translational motions. The method is tested in real image sequences.

Multiple View Geometry in Dynamic Environment

In this paper, we introduce a new multiple view geometry(MVG) which describes an absolutely dynamic environment with a dynamic scene and multiple moving cameras. The trajectories of cameras are modeled by Degree-N Bezier curve. The new MVG unifies some previous MVG into a single representation. It can describe the traditional MVG in a static environment, MVG in space-time, as well as the MVG in N-Dimention. In real image experiment, we show new MVG is very useful for generating view images.

Multiple View Geometry for Non-rigid Motions Viewed from Curvilinear Motion Projective Cameras

This paper presents a tensorial representation of multiple projective cameras with arbitrary curvilinear motions. It enables us to define multilinear relationship of image points derived from non-rigid object motions viewed from multiple cameras with arbitrary curvilinear motions. We show the new multilinear relationship is useful for generating images of non-rigid object motions viewed from cameras with arbitrary curvilinear motions. The method is tested in real image sequences.

Multiple view geometry for non-rigid motions viewed from translational cameras

This paper introduces multiple view geometry under projective projections from four-dimensional space to two-dimensional space which can represent multiple view geometry under the projection of space with time. We show the multifocal tensors defined under space-time projective projections can be derived from non-rigid object motions viewed from multiple cameras with arbitrary translational motions, and they are practical for generating images of non-rigid object motions viewed from cameras with arbitrary translational motions. The method is tested in real image sequences.

Dynamic Multiple View Geometry with Affine Cameras

A new multiple view geometry is addressed in this paper, which is obtained in a dynamic environment with a dynamic scene and moving cameras. Multiple affine cameras are considered which move along degree-\(n\) Bezier curves. The new multiple view geometry can represent the multiple view geometry in different dimensions. In the experiments, we show two applications of the new multiple view geometry: view transfer and 3D reconstruction.

Computing multiple view geometry in space-time from mutual projections of multiple cameras

The multiple view geometry in space-time can represent multiple view geometry in the case where non-rigid arbitrary motions are viewed from multiple translational cameras. However, it requires many corresponding points and is sensitive to the image noise. In this paper, we investigate mutual projections of cameras in four-dimensional space, and show it enables us to reduce the number of corresponding points required for computing the multiple view geometry in space-time. Surprisingly, we no longer need any corresponding points for computing the multiple view geometry in space-time, if all the cameras are projected to the other cameras mutually for two time intervals. We also show that the stability of the computation of multiple view geometry in space-time is drastically improved by considering the mutual projections of cameras.