Feature Generation for Adaptive Gradient-Domain Path Tracing

dc.contributor.authorBack, Jongheeen_US
dc.contributor.authorYoon, Sung-Euien_US
dc.contributor.authorMoon, Bochangen_US
dc.contributor.editorFu, Hongbo and Ghosh, Abhijeet and Kopf, Johannesen_US
dc.date.accessioned2018-10-07T14:58:01Z
dc.date.available2018-10-07T14:58:01Z
dc.date.issued2018
dc.description.abstractIn this paper, we propose a new technique to incorporate recent adaptive rendering approaches built upon local regression theory into a gradient-domain path tracing framework, in order to achieve high-quality rendering results. Our method aims to reduce random artifacts introduced by random sampling on image colors and gradients. Our high-level approach is to identify a feature image from noisy gradients, and pass the image to an existing local regression based adaptive method so that adaptive sampling and reconstruction using our feature can boost the performance of gradient-domain rendering. To fulfill our idea, we derive an ideal feature in the form of image gradients and propose an estimation process for the ideal feature in the presence of noise in image gradients. We demonstrate that our integrated adaptive solution leads to performance improvement for a gradient-domain path tracer, by seamlessly incorporating recent adaptive sampling and reconstruction strategies through our estimated feature.en_US
dc.description.number7
dc.description.sectionheadersLighting and Ray Tracing
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume37
dc.identifier.doi10.1111/cgf.13548
dc.identifier.issn1467-8659
dc.identifier.pages65-74
dc.identifier.urihttps://doi.org/10.1111/cgf.13548
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13548
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectRay tracing
dc.titleFeature Generation for Adaptive Gradient-Domain Path Tracingen_US
Files
Collections