journal article·2025-03

Reducing stereo ray‐tracing budget with 3D warping and perception‐driven reconstruction

Zhongye Shen, Chunyi Chen, Haiyang Hu, Yunbiao Liu, Ripei Zhang

Publisher page

Abstract

Abstract Monte Carlo ray tracing can produce high‐fidelity stereo renderings of 3D scenes. However, the computational costs associated with shading indirect illumination can be prohibitively expensive. While techniques like reprojection and reconstruction have been employed to reduce the inherent redundancy in stereo rendering, they often fall short in addressing issues like remaining holes and appearing artifacts, particularly in the case of specular reflections. In this paper, we introduce a stereo rendering method that leverages both ray tracing and 3D warping, incorporating techniques for reusing indirect illumination calculations and perception‐driven reconstructions. At the pre‐rendering stage, we reuse indirect illumination calculations in the background and 3D warping regions, resulting in significant savings of indirect illumination calculations in the testing scenes. For the remaining holes, we adopt a sparse sampling strategy for representative pixels, guided by saliency maps. We iteratively reconstruct indirect illumination, employing a stopping criterion based on just noticeable difference thresholds. Through equal‐sample experiments, we showcase the efficiency achieved by the proposed method in reducing high‐level sampling costs for 87.688% ~ 99.581% regions of the test scenes. Furthermore, the proposed method excels in accurately rendering both diffuse and specular reflections, ultimately enhancing the overall visual perception quality.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced Vision and Imaging · Computer Graphics and Visualization Techniques · Advanced Image Processing Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Computer Science and Technology Changchun University of Science and Technology Changchun China

Funding

National Natural Science Foundation of China

References (53)

Show source-provided references
1. 10.1109/ICCE.2017.788935310.1109/ICCE.2017.7889353 ↗
2. 10.1109/MCG.2008.12110.1109/MCG.2008.121 ↗
3. 10.1007/s11042-019-08155-210.1007/s11042-019-08155-2 ↗
4. 10.1109/IPDPSW.2016.12110.1109/IPDPSW.2016.121 ↗
5. daSilvaV VelhoL.Ray‐VR: ray tracing virtual reality in falcor.arXiv preprint arXiv:2006.11348 2020.
6. 10.1016/j.neucom.2014.10.09010.1016/j.neucom.2014.10.090 ↗
7. 10.1117/12.52476210.1117/12.524762 ↗
8. 10.1007/BF0190889510.1007/BF01908895 ↗
9. 10.1109/38.37661210.1109/38.376612 ↗
10. 10.1007/s00371005010710.1007/s003710050107 ↗
11. LiZ MarshallCS VembarDS LiuF.Future frame synthesis for fast Monte Carlo rendering in Graphics Interface 2022 2022.
12. 10.1145/280814.28088210.1145/280814.280882 ↗
13. 10.1145/311535.31157110.1145/311535.311571 ↗
14. 10.1016/j.jvcir.2016.02.01710.1016/j.jvcir.2016.02.017 ↗
15. Mara M · 2013
16. 10.1007/s00371-023-03007-510.1007/s00371-023-03007-5 ↗
17. 10.1145/337680.33772210.1145/337680.337722 ↗
18. 10.1145/336414.33641710.1145/336414.336417 ↗
19. Talbot JF · 2005
20. 10.1145/3386569.339248110.1145/3386569.3392481 ↗
21. 10.1111/cgf.1437810.1111/cgf.14378 ↗
22. Accelerating real‐time shading with reverse reprojection caching
23. Weier M · 2016 · 289
24. 10.1117/12.1991210.1117/12.19912 ↗
25. 10.1007/BF0190090310.1007/BF01900903 ↗
26. 10.1109/VR46266.2020.0010710.1109/VR46266.2020.00107 ↗
27. Visual‐perception‐driven reuse method of illumination computation in rendering stereoscopic images of 3d scenes
28. Philippi H · 2023
29. CaterK ChalmersA WardG.Detail to attention: exploiting visual tasks for selective rendering inACM International Conference Proceeding Series 2003:44:270–280.
30. 10.1145/344679010.1145/3446790 ↗
31. TakouachetN DelepoulleS RenaudC.A perceptual stopping condition for global illumination computations inProceedings of the 23rd Spring Conference on Computer Graphics.2007:55–62.10.1145/2614348.2614357 ↗
32. Harvey C · 2017 · 172
33. 10.1049/iet-cvi.2017.047810.1049/iet-cvi.2017.0478 ↗
34. 10.1007/s00371-009-0379-410.1007/s00371-009-0379-4 ↗
35. Stengel M · 2016 · 129
36. 10.1007/s00371-016-1251-y10.1007/s00371-016-1251-y ↗
37. LeeW‐J HwangSJ ShinY RyuS IhmI.Adaptive multi‐rate ray sampling on mobile ray tracing gpu inSIGGRAPH ASIA 2016 Mobile Graphics and Interactive Applications 2016:1–6.10.1145/2999508.2999523 ↗
38. GortlerSJ GrzeszczukR SzeliskiR CohenMF.The lumigraph ” inSeminal Graphics Papers: Pushing the Boundaries.2023:2453–464.10.1145/3596711.3596760 ↗
39. 10.1109/VS-Games.2014.701215910.1109/VS-Games.2014.7012159 ↗
40. DayalA WoolleyC WatsonB LuebkeD.Adaptive frameless rendering inACM SIGGRAPH 2005 Courses 2005: 24–es.10.1145/1198555.1198763 ↗
41. 10.1016/S0042-6989(96)00111-310.1016/S0042-6989(96)00111-3 ↗
42. 10.1109/34.73055810.1109/34.730558 ↗
43. Harel J · 2006
44. 10.1016/j.image.2005.04.00110.1016/j.image.2005.04.001 ↗
45. 10.1142/9789812831200_001010.1142/9789812831200_0010 ↗
46. 10.1109/SSIAI.2008.451228810.1109/SSIAI.2008.4512288 ↗
47. McMillan L · 1997
48. LangmannB HartmannK LoffeldO.Depth camera technology comparison and performance evaluation inICPRAM (2) 2012: 438–444.10.5220/0003778304380444 ↗
49. 10.1109/TRO.2017.270510310.1109/TRO.2017.2705103 ↗
50. BradleyT DebattistaK Bashford‐RogersT HarveyC DoukakisE ChalmersA.Selective BRDFs for high fidelity rendering.2016.
51. 10.1109/TIP.2004.83310510.1109/TIP.2004.833105 ↗
52. 10.1109/TIP.2007.90182010.1109/TIP.2007.901820 ↗
53. 10.1109/TPAMI.2018.281560110.1109/TPAMI.2018.2815601 ↗