Online virtual worlds have long been an anticipated medium for digital communications. They provide a compelling substrate for shared, networked environments where people can communicate, shop, socialize, collaborate, and learn. However, today's systems fall short of their imagined potential. The Meru project is designing and implementing an architecture for virtual worlds of the future. Our key insight is that a virtual model of the real world is a comfortable metaphor which addresses a wide range of issues including security, scalability, and federation. This symmetry between real and virtual worlds also permits a natural interaction between the two.

We present an efficient computational algorithm for functions represented by a nonlinear piecewise constant approximation called cuts. Our main contribution is a single traversal algorithm for merging cuts that allows for arbitrary pointwise computation, such as addition, multiplication, linear interpolation, and multi-product integration. A theoretical error bound of this approach can be proved using a statistical interpretation of cuts. Our algorithm extends naturally to computation with many cuts and maps easily to modern GPUs, leading to significant advantages over existing methods based on wavelet approximation. We apply this technique to the problem of realistic lighting and material design under complex illumination with arbitrary BRDFs. Our system smoothly integrates all-frequency relighting of shadows and reflections with dynamic per-pixel shading effects, such as bump mapping and spatially varying BRDFs. This combination of capabilities is typically missing in current systems. We represent illumination and precomputed visibility as nonlinear sparse vectors; we then use our cut merging algorithm to simultaneously interpolate visibility cuts at each pixel, and compute the triple product integral of the illumination, interpolated visibility, and dynamic BRDF samples. Finally, we present a two-pass, data-driven approach that exploits pilot visibility samples to optimize the construction of the light tree, leading to more efficient cuts and reduced datasets.

Existing techniques for fast, high-quality rendering of translucent materials often fix BSSRDF parameters at precomputation time. We present a novel method for accurate rendering and relighting of translucent materials that also enables real-time editing and manipulation of homogeneous diffuse BSSRDFs. We first apply PCA analysis on diffuse multiple scattering to derive a compact basis set, consisting of only twelve 1D functions. We discovered that this small basis set is accurate enough to approximate a general diffuse scattering profile. For each basis, we then precompute light transport data representing the translucent transfer from a set of local illumination samples to each rendered vertex. This local transfer model allows our system to integrate a variety of lighting models in a single framework, including environment lighting, local area lights, and point lights. To reduce the PRT data size, we compress both the illumination and spatial dimensions using efficient nonlinear wavelets. To edit material properties in real-time, a user-defined diffuse BSSRDF is dynamically projected onto our precomputed basis set, and is then multiplied with the translucent transfer information on the fly. Using our system, we demonstrate realistic, real-time translucent material editing and relighting effects under a variety of complex, dynamic lighting scenarios.

This paper presents a method for efficient compression and relighting with high-resolution, precomputed light transport matrices. We accomplish this using a 4D wavelet transform, transforming the columns of the transport matrix, in addition to the 2D row transform used in previous work. We show that a standard 4D wavelet transform can actually inflate portions of the matrix, because high frequency lights lead to high frequency images that cannot easily be compressed. Therefore, we present an adaptive 4D wavelet transform that terminates at a level that avoids inflation and maximizes sparsity in the matrix data. Finally, we present an algorithm for fast relighting from adaptively compressed transport matrices. Combined with a GPU-based precomputation pipeline, this results in an image and geometry relighting system that performs significantly better than 2D compression techniques, on average 2x-3x better in terms of storage cost and rendering speed for equal quality matrices.