Dynamic Depth of Field on Live Video Streams: A Stereo Solution
Zhan Yuan Yu, C. Thorpe, Xuan Yu, Scott Grauer-Gray, Feng Li, Jingyi Yu · 2011
The ability to produce dynamic Depth of Field effects in live video streams was until recently a quality unique to movie cameras. In this paper, we present a computational camera solution coupled with real-time GPU processing to produce runtime dynamic Depth of Field effects. We first construct a hybrid-resolution stereo camera with a high-res/low-res camera pair. We recover a low-res disparity map of the scene using GPU-based Belief Propagation and subsequently upsample it via fast Cross/Joint Bilateral Upsampling. With the recovered high-resolution disparity map, we warp the high-resolution video stream to nearby viewpoints to synthesize a light field towards the scene. We exploit parallel processing and atomic operations on the GPU to resolve visibility when multiple pixels warp to the same image location. Finally, we generate dynamic Depth of Field effects from the synthesized light field rendering. All processing stages are mapped onto NVIDIA’s CUDA architecture. Our system can produce Depth of Field effects with arbitrary aperture sizes and focal depths for the resolution of 640×480 at 15 fps.