Driving view simulation synthesizing virtual geometry and real images in an experimental mixed-reality traffic space

Abstract

We propose an efficient and effective image generation system for an experimental mixed-reality traffice space. Our enhanced traffic/driving simulation system represents the view through a hybrid that combines virtual geometry with real images to realize high photo-reality with little human cost. Images for datasets are captured from the real world, and the view for the simulation system is created by synthesizing image datasets with a conventional driving simulator.

Novel Stereoscopic View Generation by Image-Based Rendering Coordinated with Depth Information

“…In order to generate stereoscopic images, it is necessary to generate a novel view image from a set of images captured on the camera path. The conventional methods of stereoscopic view generation suffer from the distortion due to vertical parallax [11,12]. Our method employs the light field rendering [13] same as the conventional method, and tries to reduce the distortion of generated image by rendering coordinated with depth information.…”