StyLit: Example-Based Stylization of 3D Renderings
Subscribe:  iCal  |  Google Calendar
Amsterdam NL   25, Jun — 28, Jun
Los Angeles US   25, Jun — 28, Jun
Montreal CA   27, Jun — 1, Jul
Cambridge GB   28, Jun — 2, Jul
Guildford GB   29, Jun — 30, Jun
Latest comments
1 hours ago

Great job! I want this too! Please make it somehow available!

by John Doe
2 hours ago

I want this!

by hnjmbn
3 hours ago


StyLit: Example-Based Stylization of 3D Renderings
29 June, 2017

Some of you might have missed this crazy thing called StyLit algorithm. The system for example-based stylization of 3D renderings was originally published by Fišer et al. at SIGGRAPH 2016 and demonstrated at Adobe MAX 2016. The project allows you to paint or draw over a printed stencil and see your unique style to be transferred in real-time on a variety of 3D models. The best thing is that you can try it for yourself!

We present an approach to example-based stylization of 3D renderings that better preserves the rich expressiveness of hand-created artwork. Unlike previous techniques, which are mainly guided by colors and normals, our approach is based on light propagation in the scene.

This novel type of guidance can distinguish among context-dependent illumination effects, for which artists typically use different stylization techniques, and delivers a look closer to realistic artwork. In addition, we demonstrate that the current state of the art in guided texture synthesis produces artifacts that can significantly decrease the fidelity of the synthesized imagery, and propose an improved algorithm that alleviates them. Finally, we demonstrate our method’s effectiveness on a variety of scenes and styles, in applications like interactive shading study or autocompletion.

Fišer et al.

So, how does one try it? You just need to download the app, print these forms and paint! Besides live video input you can also use Screen Capture mode where you can display the stencil on the screen and modify it using some digital painting tool such as Adobe Photoshop.

Hardware/Software Requirements:

The demo should run on any recent PC with powerful GPU (e.g., GeForce GTX 970) and CPU (e.g., Core i7). Windows 10/8/7 with latest CUDA drivers need to be installed. Any camera with DirectShow support can be used for live video capture, e.g., Logitech C920 or any recent Android smartphone equipped with IP Webcam app and IP Webcam Adapter 2.0 installed on PC.

Source: StyLit

Leave a Reply