A Fast Kd-tree Construction for Ray Tracing based on Efficient Ray Distribution

Liang, Xiao; Yang, Hongyu; Qian, Yuguo; Zhang, Yanci

doi:10.4304/jsw.9.3.596-604

Cited by 2 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Figs. 8 and 9) show the high quality of the produced depth images for the same two models used in [35]. (Table 2) shows that our proposed algorithm, Enhanced RT, has the highest successful hit rate which means that, it is the most efficient algorithm.…”

Section: Resultsmentioning

confidence: 92%

“…Also Enhanced RT achieved better image quality than zbuffer but z-buffer achieved better running time. In comparison with fast kd-tree construction for ray tracing algorithm based on efficient ray distribution [35], Enhanced RT achieved better successful rate which indicates that Enhanced RT succeeded in decreasing the total ray object intersection. In this paper we introduced an enhanced ray tracing (Enhanced RT) algorithm, and its implementation, which used to get the depth images for retrieving non-rigid 3D objects based on rendering the 3D model as a set of depth images from multiple view directions.…”

Section: Resultsmentioning

confidence: 98%

“…The proposed algorithm achieved a very good compromise between the quality of the generated depth images and the algorithm's execution time. A comparison performed between our proposed algorithm and one of the most recent ray tracing algorithms, the fast kd-tree construction for ray tracing based on efficient ray distribution [35], was down using successful hit rate as shown in (Table 2 and Fig. 7).…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Enhanced Ray Tracing Algorithm for Depth Image Generation

Ahmed

Shedeed

Hegazy

2015

BJMCS

View full text Add to dashboard Cite

Ray tracing is a method to convert 3D image to high quality 2D realistic image. In traditional Ray tracing technique generating an image is an expensive process due to the large number of transmitted rays and the intersection tests of these rays with the scene primitives. This paper introduces an enhanced ray tracing (Enhanced RT) algorithm. In the proposed algorithm, merge sort algorithm is used to order triangles according to the minimum x coordinate. Then Binary Search algorithm is used to find the end index of the first triangle that has minimum x coordinate greater than the pixel x coordinate. This search limits the subset of the triangles that may intersect the ray, and hence, reduces the intersection calculation time. Experimental results show that the proposed algorithm decreased the execution time by 99.8% than the traditional ray tracing algorithm with high quality for the produced depth images for a standard Benchmark models. The implementation was done on an ordinary hardware without need to use the highly expensive parallel architecture hardware (as GPUs or Clusters) as in the other research in the same application. The proposed algorithm also achieved the highest successful hit rate in comparing to the most recent ray tracing algorithms.

show abstract

Section: Resultsmentioning

confidence: 92%

Section: Resultsmentioning

confidence: 98%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced Ray Tracing Algorithm for Depth Image Generation

Ahmed

Shedeed

Hegazy

2015

BJMCS

View full text Add to dashboard Cite

show abstract

“…Wächter and Keller [24] introduce Bounding Interval Hierarchy (BIH) where the maximum memory usage is linearly bounded by the number of primitives. Liang et al [15] use a stream based partial construction. An on-demand construction algorithm is also employed.…”

Section: On-demand Construction For Ray Tracingmentioning

confidence: 99%

Efficient kd-tree construction for ray tracing using ray distribution sampling

Liang

Yang

Zhang

et al. 2015

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Although regarded as a standard heuristic for constructing a kd-tree, Surface Area Heuristic (SAH) suffers from degrading traversal performance as well as unnecessary acceleration structure construction due to its assumption of uniform ray distribution. In this paper, first, we propose a Grid based Ray Distribution Heuristic (GRDH) to construct a high quality kd-tree. The information of ray distribution is sampled and recorded in a sparse grid, which is also utilized to partition primitives efficiently. The heuristic only evaluating traversal cost on limited splitting candidates, is fast and easy to be implemented. Then, we introduce a novel ray tracing pipeline with two-pass construction and two-pass tracing routine to enable an ondemand construction algorithm. In the pipeline, after constructing a partially structured kd-tree, rays are classified by whether triggering transitions to construct unstructured leaf nodes, and being traced in different tracing passes. For on-demand construction, this raises the barrier of interleaving with traversal routine, as well as enables the algorithm to be flexible on multi-core computation platform. Additionally, GRDH is also combined into on-demand construction for high traversal performance. The experimental results demonstrate that the on-demand GRDH construction algorithm can achieve a speedup of 1.63~1.95 in overall frame performance for scenes with more than 360K primitives.

show abstract

A Fast Kd-tree Construction for Ray Tracing based on Efficient Ray Distribution

Cited by 2 publications

References 19 publications

Enhanced Ray Tracing Algorithm for Depth Image Generation

Enhanced Ray Tracing Algorithm for Depth Image Generation

Efficient kd-tree construction for ray tracing using ray distribution sampling

Contact Info

Product

Resources

About