Ray Casting Deformable Models on the GPU

Patidar, Suryakant; Narayanan, P. J.

doi:10.1109/icvgip.2008.92

Cited by 7 publications

(8 citation statements)

References 18 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kd-trees and BVHs are still expensive to build on GPU, especially if they need to be built every frame. Patidar and Narayanan used a perspective grid to raycast dynamic scenes using a fast building of the grid in each frame [3]. Their triangle storage layout is shown in Fig.…”

Section: Background and Previous Workmentioning

confidence: 99%

“…Wald et al [13] presented an algorithm to traverse the grid in a slice-wise coherent manner. Due to the use of a frustum like grid, Hunt and Mark [14] and Patidar and Narayanan [3] treat primary rays as coherent packets of rays. These packets of rays work together bringing optimal amount of data and reusing it.…”

Section: Background and Previous Workmentioning

confidence: 99%

“…We use a perspective grid in camera space for the primary rays and a perspective grid in light space for shadow rays, building on our earlier work [3], [4]. Camera-space perspective grid provides perfect coherence to primary rays.…”

Section: Introductionmentioning

confidence: 99%

“…Frustum culling and back-face culling (BFC) reduce the geometry to be processed as the grid is built per frame. The user-managed shared memory of the GPU is used effectively for the tracing step [3]. We build a grid of smaller voxels to limit the number of triangles in each but trace multiple voxels together to better exploit the the large SIMD width on GPUs [4].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Raytracing Dynamic Scenes on the GPU Using Grids

Guntury

Narayanan

2012

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Abstract-Raytracing dynamic scenes at interactive rates have received a lot of attention recently. We present a few strategies for high performance raytracing on a commodity GPU. The construction of grids needs sorting, which is fast on today's GPUs. The grid is thus the acceleration structure of choice for dynamic scenes as per-frame rebuilding is required. We advocate the use of appropriate data structures for each stage of raytracing, resulting in multiple structure building per frame. A perspective grid built for the camera achieves perfect coherence for primary rays. A perspective grid built with respect to each light source provides the best performance for shadow rays. Spherical grids handle lights positioned inside the model space and handle spotlights. Uniform grids are best for reflection and refraction rays with little coherence. We propose an Enforced Coherence method to bring coherence to them by rearranging the ray to voxel mapping using sorting. This gives the best performance on GPUs with only user-managed caches. We also propose a simple, Independent Voxel Walk method, which performs best by taking advantage of the L1 and L2 caches on recent GPUs. We achieve over 10 fps of total rendering on the Conference model with one light source and one reflection bounce, while rebuilding the data structure for each stage. Ideas presented here are likely to give high performance on the future GPUs as well as other manycore architectures.

show abstract

Section: Background and Previous Workmentioning

confidence: 99%

Section: Background and Previous Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Raytracing Dynamic Scenes on the GPU Using Grids

Guntury

Narayanan

2012

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…Their approach is limited to computing a boundary representation of the scene, which is only a part of the information required for ray tracing. Patidar and Narayanan [2008] propose a fast construction algorithm for a gridlike acceleration structure, but their algorithm is limited to fixed resolution and while it performs well for scanned models, it relies on synchronization via atomic functions which makes it sensitive to triangle distributions. Ize et al [2006] describe a number of parallel construction algorithms for multiple CPUs.…”

Section: Previous Workmentioning

confidence: 99%

A parallel algorithm for construction of uniform grids

Kalojanov

Slusallek

2009

Proceedings of the Conference on High Performance Graphics 2009

View full text Add to dashboard Cite

We present a fast, parallel GPU algorithm for construction of uniform grids for ray tracing, which we implement in CUDA. The algorithm performance does not depend on the primitive distribution, because we reduce the problem to sorting pairs of primitives and cell indices. Our implementation is able to take full advantage of the parallel architecture of the GPU, and construction speed is faster than CPU algorithms running on multiple cores. Its scalability and robustness make it superior to alternative approaches, especially for scenes with complex primitive distributions.

show abstract

A Study of Software Architecture for Real-Time Image and Graphic Processing for Time-Sequenced 3-D CT Images

Yanagihara¹

2012

Advances in Intelligent and Soft Computing

View full text Add to dashboard Cite

Ray Casting Deformable Models on the GPU

Cited by 7 publications

References 18 publications

Raytracing Dynamic Scenes on the GPU Using Grids

Raytracing Dynamic Scenes on the GPU Using Grids

A parallel algorithm for construction of uniform grids

A Study of Software Architecture for Real-Time Image and Graphic Processing for Time-Sequenced 3-D CT Images

Contact Info

Product

Resources

About