Abstract

A real-time multi-GPU color holographic video display system computes holograms from 3D video of a rigid object. System has three main stages; client, server and optics. 3D coordinate and texture information are kept in client and sent online to the server through the network. In the server stage, with the help of the parallel processing ability of the GPUs and segmentation algorithms, phase-holograms are computed in real-time. The graphic card of the server computer drives the SLMs and red, green and blue channels are controlled in parallel. Resultant color holographic video is loaded to the SLMs which are illuminated by expanded light from LEDs. In the optics stage, reconstructed color components are combined by using beam splitters. Reconstructions are captured by a CCD array without any supporting optics. Experimental results are satisfactory.

Paper available at IEEE.

Video editing is currently at two simultaneous inflections points: use of GPUs for video processing and the beginning of wide spread adoption of 3D. At this time however, identifying and navigating through the necessary tools and equipment to create compelling 3D video content is challenging. This session is intended to provide a pragmatic guide to creating prosumer 3D video content and how the GPU greatly assists and speeds up this process. The intended audience is anyone interested in how to create compelling 3D movies at a prosumer level.

The arrival of fully programable GPUs is now changing the visual effects industry, which traditionally relied on CPU computation to create their spectacular imagery. Implementing the complex image processing algorithms used by VFX is a challenge, but the payoffs in terms of interactivity and throughput can be enormous. Hear how The Foundry's novel image processing architecture simplifies the implementation of GPU-enabled VFX software and eases the transition from a CPU based infrastructure to a GPU based one.

Video from aerial surveillance can provide a rich source of data for many applications and can be enhanced for display and analysis through such methods as mosaic construction, super-resolution, and mover detection. All of these methods require accurate frame-to-frame registration, which for live use must be performed in real time. In many situations, scene parallax may make alignment using global transformations impossible or error-prone, limiting the performance of subsequent processing and applications. For these cases, dense (per-pixel) correspondence is required, but this can be computationally prohibitive. This paper presents a hierarchical dense correspondence algorithm designed for implementation on graphics processing units (GPUs). Since the method does not rely on epipolar geometry, it is also suitable for use when there are uncorrected nonlinear lens distortions. A framework for using this dense correspondence to implement local mosaicking, super-resolution enhancement, and mover detection is also presented and demonstrated using examples of each of these types of enhancement and different types of video sources.

Paper available at ACM.

This paper presents an interactive GPU-based system for cinematic relighting with multiple-bounce indirect illumination from a fixed view-point. We use a deep frame-buffer containing a set of view samples, whose indirect illumination is recomputed from the direct illumination on a large set of gather samples, distributed around the scene. This direct-to-indirect transfer is a linear transform which is particularly large, given the size of the view and gather sets. This makes it hard to precompute, store and multiply with. We address this problem by representing the transform as a set of sparse matrices encoded in wavelet space. A hierarchical construction is used to impose a wavelet basis on the unstructured gather cloud, and an image-based approach is used to map the sparse matrix computations to the GPU. We precompute the transfer matrices using a hierarchical algorithm and a variation of photon mapping in less than three hours on one processor. We achieve high-quality indirect illumination at 10-20 frames per second for complex scenes with over 2 million polygons, with diffuse and glossy materials, and arbitrary direct lighting models (expressed using shaders). We compute per-pixel indirect illumination without the need of irradiance caching or other subsampling techniques.

Paper available at ACM.