Virtual view synthesis for 3D light-field display based on scene tower blending

Dynamic Field of View in a Tomographic Light Field Display

We also demonstrate the effectiveness of SART in generating dynamic real-time scenes (20 fps on an Nvidia Pascal GPU). Unlike traditional 2D displays, light field displays provide binocular depth cues such as high-resolution motion parallax, occlusion, translucency, and specularity. In particular attenuation-based light field displays provide an inexpensive means by which to produce these unenc...

The Tower: Constructing a 3D Scene

Reconstructing Dense Light Field from Multi-Focus Images Array for Virtual View Synthesis

This paper presents a novel method for synthesizing a novel view from two sets of differently focused images taken by an aperture camera array for a scene of two approximately constant depths. The proposed method consists of two steps. The first step is a view interpolation to reconstruct an all in-focus dense light field of the scene. The second step is to synthesize a novel view by light fiel...

Dynamic Scene Reconstruction for 3D Virtual Guidance

In this paper a system is presented able to reproduce the actions of multiple moving objects into a 3D model. A multi-camera system is used for automatically detect, track and classify the objects. Data fusion from multiple sensors allows to get a more precise estimation of the position of detected moving objects and to solve occlusions problem. These data are then used to automatically place a...

Multi–view Autostereoscopic 3d Display

Autostereoscopic displays provide 3D perception without the need for special glasses or other head gear. Three basic technologies exist to make such displays: spatial multiplex, multi-projector and time-sequential. These can be used to make two types of useful device: two-view, head-tracked displays; and multi-view displays. The former tend to be single-viewer systems while the latter can suppo...