TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Machine Learning Is the Solution Also for Foveated Path Tracing Reconstruction

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoProceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP
KustantajaSCITEPRESS
Sivut361-367
ISBN (elektroninen)978-989758402-2
DOI - pysyväislinkit
TilaJulkaistu - helmikuuta 2020
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaInternational conference on computer graphics theory and applications - Valletta, Malta
Kesto: 27 helmikuuta 202029 helmikuuta 2020

Conference

ConferenceInternational conference on computer graphics theory and applications
MaaMalta
KaupunkiValletta
Ajanjakso27/02/2029/02/20

Tiivistelmä

Real-time photorealistic rendering requires a lot of computational power. Foveated rendering reduces the work by focusing the effort to where the user is looking, but the very sparse sampling in the periphery requires fast reconstruction algorithms with good quality. The problem is even more complicated in the field of foveated path tracing where the sparse samples are also noisy. In this position paper we argue that machine learning and data-driven methods play an important role in the future of real-time foveated rendering. In order to show initial proofs to support this opinion, we propose a preliminary machine learning based method which is able to improve the reconstruction quality of foveated path traced image by using spatio-temporal input data. Moreover, the method is able to run in the same reduced foveated resolution as the path tracing setup. The reconstruction using the preliminary network is about 2.9ms per 658 × 960 frame on a GeForce RTX 2080 Ti GPU.

Julkaisufoorumi-taso