CPU-GPU Multithreaded Programming Model: Application to the Path Tracing with Next Event Estimation Algorithm

Cassagnabère, Christophe; Rousselle, François; Renaud, Christophe

doi:10.1007/11919629_28

Cited by 2 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A relatively complete table which summarizes the accelerating techniques of ray tracing appears in (Arvo and Kirk, 1987;Amanatides, 1984;Ghazanfarpour and Hasenfratz, 1998;Glassner, 1984;Kay and Kajiya, 1986;Shinya et al, 1987). Recently, many accelerating algorithm (Cassagnabere et al, 2006) which based on the GPUs algorithm in order to optimize the ray triangle intersection calculation.…”

Section: Fig 1: Scene Plane With Armentioning

confidence: 99%

An Alternative Ray Tracing Algorithm for Understanding Scenes with Embedded Objects

Dandachy¹,

Plemenos²,

Chendeb³

et al. 2010

Journal of Computer Science

View full text Add to dashboard Cite

Problem statement: In the virtual world domain, the existing techniques of exploration, were not able alone to resolve the understanding problem of scenes with embedded object, also they are time and memory consuming. As a solution, a novel method that enhances the visualization of 3D ray traced scenes with embedded objects by creating a hole proportional to its interior parts was developed and tested. Approach: This research presented a novel approach that allows an automatic exploration of 3D scenes with embedded objects. First of all, the apparent contour of the interior object that we want to see, were computed by using the ray tracing algorithm with the selective refinement optimization approach. The second step was to search for pixels which are orthogonal in a certain depth and directed toward the outside of the silhouette in order to create a hole. Results: The obtained results were convincing and answering to the goal of this research. The proposed method allows the creation of a hole around an object and can be applied to any type of model. Conclusion: This very successful approach for 3D scenes with embedded object exploration is further supported by its ability to give at the same time a global idea about the scene as well as a possibility to explore its interior while saving time and memory

show abstract