What a busy week this has been! I was able to get following done:
And I still have this Friday left! Feeling great and it’s getting better. 🙂
If only my papers would get such great reviews! 😉
A teaser of my upcoming talk at CESCG 2015. It’s going to be lots of fun! 😉 The full program will be up here soon.
The Rendering course lectures are going online this year!
If you’d like to see updates from the channel, you can subscribe to it.
I have had an awful lot of fun with Google DeepMind’s Deep Q-learning algorithm. It plays Atari Breakout solely based on relying the sensory input, and doesn’t know anything about the game when starting out.
I have also added a patch to fix the visualization when reloading a pre-trained network. The window will appear after the first evaluation batch is done (typically a few minutes). This configuration is able to run Ilya Kuzovkin’s version using less than 1GB VRAM.
To demonstrate the simplicity of our technique, we have implemented Separable Subsurface Scattering in a less than 4 kilobyte binary executable file. This is the whole thing:
Details are available here. Greetings to elites!
Three new interviews are now available:
– DSOGaming in English,
– SG.hu in Hungarian,
– PC Games Hardware in German,
Check them out!
Just got back from KÉPAF 2015, a domestic computer vision and shape recognition conference. We had a great time with an electronic poster session and some great outdoor events involving all kinds of horseback riding. Thank you!
Some footage made with LuxRender was shown during the Academy Awards. I have to admit that I reserved this Oscar-award image to posts involving any prizes and awards, and now there you go! 🙂 I’m so proud!
Kevin Streicher wrote an excellent tech report as a seminar work in computer graphics. Congratulations!
