Learning Generic Local Shape Properties for Adaptive Super-Sampling
| dc.contributor.author | Reinbold, Christian | en_US |
| dc.contributor.author | Westermann, Rüdiger | en_US |
| dc.contributor.editor | Pelechano, Nuria | en_US |
| dc.contributor.editor | Vanderhaeghe, David | en_US |
| dc.date.accessioned | 2022-04-22T08:16:14Z | |
| dc.date.available | 2022-04-22T08:16:14Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | We propose a novel encoder/decoder-based neural network architecture that learns view-dependent shape and appearance of geometry represented by voxel representations. Since the network is trained on local geometry patches, it generalizes to arbitrary models. A geometry model is first encoded into a sparse voxel octree of features learned by a network, and this model representation can then be decoded by another network in-turn for the intended task. We utilize the network for adaptive supersampling in ray-tracing, to predict super-sampling patterns when seeing coarse-scale geometry. We discuss and evaluate the proposed network design, and demonstrate that the decoder network is compact and can be integrated seamlessly into on-chip ray-tracing kernels. We compare the results to previous screen-space super-sampling strategies as well as non-network-based world-space approaches. | en_US |
| dc.description.sectionheaders | Learning | |
| dc.description.seriesinformation | Eurographics 2022 - Short Papers | |
| dc.identifier.doi | 10.2312/egs.20221032 | |
| dc.identifier.isbn | 978-3-03868-169-4 | |
| dc.identifier.issn | 1017-4656 | |
| dc.identifier.pages | 57-60 | |
| dc.identifier.pages | 4 pages | |
| dc.identifier.uri | https://doi.org/10.2312/egs.20221032 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/egs20221032 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.title | Learning Generic Local Shape Properties for Adaptive Super-Sampling | en_US |
Files
Original bundle
1 - 1 of 1