Real-Time Hair Filtering with Convolutional Neural Networks
Journal article, 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.

real-time

neural networks

transparency

filtering

hair

Author

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

25776193 (eISSN)

Vol. 5 1 15

Real-time Photo-realistic Rendering

Swedish Research Council (VR) (2014-4559), 2014-01-01 -- 2021-12-31.

Komprimering av förberäknad belysningsinformation

Swedish Research Council (VR) (2017-05060), 2018-01-01 -- 2021-12-31.

Subject Categories

Computer Engineering

Computer Science

DOI

10.1145/3522606

More information

Latest update

4/21/2023