Historical buildings are a treasure of human cultural heritage, but reconstructing them from archival photos is hard: images are few, quality is poor, scenes have changed over time, and most photos are grayscale.
Drag to look around, click on floor markers to select camera view and press , or . to step through cameras.
We introduce an approach to reconstruct the 3D geometry of historical buildings using volumetric rendering. We leverage dense point clouds as a geometric prior and introduce a color appearance embedding loss to recover building color from a handful of available color images.
Continue Reading →
During the last 6 month I have been working on HandVR, a personalized VR experience.
At the end of the 6 month Lift program at KiBu I had the opportunity to present the results at Startup Safari.
In this demo the user has photo realistic hand models instead of seeing the controllers.
Continue Reading →
For a truly immersive experience
I've always preferred story-driven games to the competitive ones. When diving into a game like this, one experiences a variety of emotions and may also grow as a person at the end. Despite all that I came to the realization that we might control these characters — our avatars in a way—, but in effect, they have nothing to do with us!
When playing a game, you see the body and hands of your playable avatar instead of your own. You can customize your character in some MMORPGs, but it still requires heavy manual tweaking to make them look like you.
This is even more relevant in virtual reality, where the control is, literally, in the player's hands. Hand-object interaction is in the center of a great virtual reality experience.
Continue Reading →
Since last summer I have been working on establishing a new definition for Anime and Cartoon using Artificial Intelligence.
During this time I took part in the KiBu Lift Program and the Hungarian National Talent Program.
Continue Reading →
This post is the continuation of Anime or Cartoon? – Let the AI decide. In it I describe the project I’m collecting the data for.
In Deep Learning we often work with huge datasets and this project is no exception. I collected around 300.000 images from both anime and cartoons. Processing this many images is not an easy task though. After downloading the images from various sources, I quickly looked into them and found a few potential issues…
Continue Reading →
There is an ongoing debate about the definition of Anime.
The word anime (アニメ) comes from the abbreviated pronunciation of “animation” in Japanese, referring to all kinds of animation.
Outside of Japan however, it is usually meant as animations exclusively created in Japan.
Continue Reading →
Deep learning is currently a hot topic in Machine learning. The best way to illustrate this is probably through Neural Style Transfer. To get a better understanding of how this technique works I created a couple of images with the original code:
Golden bridge with the style of a snowy scene from Kara no Kyoukai – The Garden of Sinner
Golden bridge with the style of an apocalyptic scene from the same anime
Continue Reading →
I’ve got access to an HTC Vive recently thanks to Kibu and I spent my past few weeks playing most of the games available. In this post I’ll share what I’ve learned from playing these games and watching others play them. I’ll walk around the different design solutions in these games especially applied to the Vive.
Continue Reading →
The campers & their drones
After a long year of learning about drones we traveled to Lake Balaton for a weekend to finally build them! During the weekend we assembled two quadcopters and modified an existing one to enable mobile control.
Continue Reading →
Atmo at the Demo Day
During the last 6 months I was in the Atmo team to develop a working prototype for an interactive board game extension as part of the Talent program at Kitchen Budapest.
Continue Reading →
