Volume is a tool for reconstructing a single 2D image or video in 3D space. Using state-of-the-art machine learning research, Volume is able to generate a 3D asset from a single view. Volume is currently under development and is being built as an end-to-end solution allowing anyone to easily generate a 3D asset and use it in 3D environments. We provide special templates for easily using Volume assets in virtual, augmented and mixed reality platforms.
Volume supports exporting bundled assets directly to Unity3D, Unreal and Three.js using custom exporters. Working on a platform that is not listed? we want to know
We are developing Volume as both a web service and a comptuer vision API allowing maxium flexability trough user interface or embedding it in your existing sofrware pipeline. Volume is made by Or Fleisher and Shirin Anlen.
Volume is built through experimentation at its essence. We are always exploring different uses, platforms, and aesthetics that could drive new types of stories we haven't been able to tell before.
Augmented Reality / 2018
Inside Pulp Fiction is an Augmented Reality experiment that uses Volume's reconstruction tool to build Pulp Fiction's iconic dance scene in your own space.
Mac, Linux, Windows / 2017
ReTouch is an OpenGL application that enables editing and retouching of images using depth-maps in 2.5D. Color and edit the background and foreground separately, given any image.