Show simple item record

dc.contributor.authorManzi, Marco
dc.contributor.authorKettunen, Markus
dc.contributor.authorDurand, Frédo
dc.contributor.authorZwicker, Matthias
dc.contributor.authorLehtinen, Jaakko
dc.date.accessioned2021-10-27T20:06:07Z
dc.date.available2021-10-27T20:06:07Z
dc.date.issued2016
dc.identifier.urihttps://hdl.handle.net/1721.1/134673
dc.description.abstract© 2016 Copyright held by the owner/author(s). We present a novel approach to improve temporal coherence in Monte Carlo renderings of animation sequences. Unlike other approaches that exploit temporal coherence in a post-process, our technique does so already during sampling. Building on previous gradient-domain rendering techniques that sample finite differences over the image plane, we introduce temporal finite differences and formulate a corresponding 3D spatio-temporal screened Poisson reconstruction problem that is solved over windowed batches of several frames simultaneously. We further extend our approach to include second order, mixed spatio-temporal differences, an improved technique to compute temporal differences exploiting motion vectors, and adaptive sampling. Our algorithm can be built on a gradient-domain path tracer without large modifications. In particular, we do not require the ability to evaluate animation paths over multiple frames. We demonstrate that our approach effectively reduces temporal flickering in animation sequences, significantly improving the visual quality compared to both path tracing and gradient-domain rendering of individual frames.
dc.language.isoen
dc.publisherAssociation for Computing Machinery (ACM)
dc.relation.isversionof10.1145/2980179.2980256
dc.rightsCreative Commons Attribution 4.0 International license
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.sourceACM
dc.titleTemporal gradient-domain path tracing
dc.typeArticle
dc.identifier.citationManzi, Marco, et al. "Temporal Gradient-Domain Path Tracing." Acm Transactions on Graphics 35 6 (2016): 9.
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
dc.relation.journalACM Transactions on Graphics
dc.eprint.versionFinal published version
dc.type.urihttp://purl.org/eprint/type/JournalArticle
eprint.statushttp://purl.org/eprint/status/PeerReviewed
dc.date.updated2019-05-29T13:02:41Z
dspace.orderedauthorsManzi, M; Kettunen, M; Durand, F; Zwicker, M; Lehtinen, J
dspace.date.submission2019-05-29T13:02:44Z
mit.journal.volume35
mit.journal.issue6
mit.metadata.statusAuthority Work and Publication Information Needed


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record