Abstract We present a practical importance‐driven method for GPU‐based final gathering. We take as input a point cloud representing directly illuminated scene geometry; we then project and splat the points to microbuffers, which store each shading pixel's occluded radiance field. We select points for projection based on importance, defined as each point's estimated contribution to a shading pixel. For each selected point, we calculate its splat size adaptively based on its importance value. The main advantage of our method is that it's simple and fast, and provides the capability to incorporate additional importance factors such as glossy reflection paths. We also introduce an image‐space adaptive sampling method, which combines adaptive image subdivision with joint bilateral upsampling to robustly preserve fine details. We have implemented our algorithm on the GPU, providing high‐quality rendering for dynamic scenes at near interactive rates.

The ability to place surface samples with Poisson disk distribution can benefit a variety of graphics applications. Such a distribution satisfies the blue noise property, i.e. lack of low frequency noise and structural bias in the Fourier power spectrum. While many techniques are available for sampling the plane, challenges remain for sampling arbitrary surfaces. In this paper, we present new methods for Poisson disk sampling with spectrum analysis on arbitrary manifold surfaces. Our first contribution is a parallel dart throwing algorithm that generates high-quality surface samples at interactive rates. It is flexible and can be extended to adaptive sampling given a user-specified radius field. Our second contribution is a new method for analyzing the spectral quality of surface samples. Using the spectral mesh basis derived from the discrete mesh Laplacian operator, we extend standard concepts in power spectrum analysis such as radial means and anisotropy to arbitrary manifold surfaces. This provides a way to directly evaluate the spectral distribution quality of surface samples without requiring mesh parameterization. Finally, we implement our Poisson disk sampling algorithm on the GPU, and demonstrate practical applications involving interactive sampling and texturing on arbitrary surfaces.