Browsing by Author "Vaidyanathan, Karthik"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Ray Tracing Lossy Compressed Grid Primitives
    (The Eurographics Association, 2021) Benthin, Carsten; Vaidyanathan, Karthik; Woop, Sven; Theisel, Holger and Wimmer, Michael
    We propose a new watertight representation of geometry for ray tracing highly complex scenes in a memory efficient manner. Polygon meshes in the scene are first converted into compressed grid primitives, which are represented by a base bilinear patch with quantized displacement vectors. Ray-scene intersections are then computed by efficiently decompressing these grids onthe- fly and intersecting the implicit triangles. Our representation requires just 5:4??6:6 bytes per triangle for the combined geometry and acceleration structure, resulting in a 5-7x reduction in memory footprint compared to indexed triangle meshes. This is achieved with less than 15% increase in rendering time.
  • No Thumbnail Available
    Item
    Temporally Stable Real-Time Joint Neural Denoising and Supersampling
    (ACM Association for Computing Machinery, 2022) Thomas, Manu Mathew; Liktor, Gabor; Peters, Christoph; Kim, Sungye; Vaidyanathan, Karthik; Forbes, Angus G.; Josef Spjut; Marc Stamminger; Victor Zordan
    Recent advances in ray tracing hardware bring real-time path tracing into reach, and ray traced soft shadows, glossy reflections, and diffuse global illumination are now common features in games. Nonetheless, ray budgets are still limited. This results in undersampling, which manifests as aliasing and noise. Prior work addresses these issues separately. While temporal supersampling methods based on neural networks have gained a wide use in modern games due to their better robustness, neural denoising remains challenging because of its higher computational cost. We introduce a novel neural network architecture for real-time rendering that combines supersampling and denoising, thus lowering the cost compared to two separate networks. This is achieved by sharing a single low-precision feature extractor with multiple higher-precision filter stages. To reduce cost further, our network takes low-resolution inputs and reconstructs a high-resolution denoised supersampled output. Our technique produces temporally stable high-fidelity results that significantly outperform state-of-the-art real-time statistical or analytical denoisers combined with TAA or neural upsampling to the target resolution. We introduce a novel neural network architecture for real-time rendering that combines supersampling and denoising, thus lowering the cost compared to two separate networks. This is achieved by sharing a single low-precision feature extractor with multiple higher-precision filter stages. To reduce cost further, our network takes low-resolution inputs and reconstructs a high-resolution denoised supersampled output. Our technique produces temporally stable high-fidelity results that significantly outperform state-of-the-art real-time statistical or analytical denoisers combined with TAA or neural upsampling to the target resolution.
  • Thumbnail Image
    Item
    Wide BVH Traversal with a Short Stack
    (The Eurographics Association, 2019) Vaidyanathan, Karthik; Woop, Sven; Benthin, Carsten; Steinberger, Markus and Foley, Tim
    Compressed wide bounding volume hierarchies can significantly improve the performance of incoherent ray traversal, through a smaller working set of inner nodes and therefore a higher cache hit rate. While inner nodes in the hierarchy can be compressed, the size of the working set for a full traversal stack remains a significant overhead. In this paper we introduce an algorithm for wide bounding volume hierarchy (BVH) traversal that uses a short stack of just a few entries. This stack can be fully stored in scarce on-chip memory, which is especially important for GPUs and dedicated ray tracing hardware implementations. Our approach in particular generalizes the restart trail algorithm for binary BVHs to BVHs of arbitrary widths. Applying our algorithm to wide BVHs, we demonstrate that the number of traversal steps with just five stack entries is close to that of a full traversal stack. We also propose an extension to efficiently cull leaf nodes when a closer intersection has been found, which reduces ray primitive intersections by up to 14%.