Real-Time Hair Filtering with Convolutional Neural Networks
Paper i proceeding, 2022

Rendering of realistic-looking hair is in general still too costly to do in real-time applications, from simulating the physics to rendering the fine details required for it to look natural, including self-shadowing.We show how an autoencoder network, that can be evaluated in real time, can be trained to filter an image of few stochastic samples, including self-shadowing, to produce a much more detailed image that takes into account real hair thickness and transparency.

hair

transparency

real-time

filtering

neural networks

Författare

Roc Ramon Currius

Embedded Electronics Systems and Computer Graphics

Ulf Assarsson

Embedded Electronics Systems and Computer Graphics

Erik Sintorn

Embedded Electronics Systems and Computer Graphics

Proceedings of the ACM on Computer Graphics and Interactive Techniques

2577-6193 (eISSN)

Vol. 5 1 15

ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, I3D 2022
Online, ,

Fotorealistisk rendering för realtid

Vetenskapsrådet (VR) (2014-4559), 2014-01-01 -- 2021-12-31.

Komprimering av förberäknad belysningsinformation

Vetenskapsrådet (VR) (2017-05060), 2018-01-01 -- 2021-12-31.

Ämneskategorier

Datorteknik

Datavetenskap (datalogi)

DOI

10.1145/3522606

Mer information

Skapat

2022-05-06