SIGGRAPH is often a play space for new imaging software, where academics get a chance to show off the weird and wonderful software they've been working on for years. As SIGGRAPH Asia 2013 this November, one group wants to demo a piece of software that can take a single image, and generate a 3D object out of something in it. Dubbed, it relies on a user making three quick selections around the object in order to interpret the size and shape. From there, it can be rotated in three dimensions, edited, moved into other photos, and more. It allows real world objects to be resized and tweaked for digital use, and easily manipulated. The video below shows off something of what the software is potentially capable of, and the areas where it struggles.

But for someone looking to pull together 3D objects easily, it seems simple and impressive.

3-Sweep: Extracting Editable Objects from a Single Photo 1,2,3,Zhe Zhu 1, 3, 1, 2 1TNList, Department of Computer Science and Technology, Tsinghua University 2Tel Aviv University 3The Interdisciplinary Center 3-Sweep Object Extraction. (a) Input image. Songbook Vol 1 Mika.

(b) Extracted edges. (c) 3-Sweep modeling of one component of the object. (d) The full extracted 3D model. (e) Editing the model by rotating each arm in a different direction, and pasting onto a new background. The base of the object is transferred by alpha matting and compositing. Abstract We introduce an interactive technique for manipulating simple 3D shapes based on extracting them from a single photograph. Such extraction requires understanding of the components of the shape, their projections, and relations.

Sep 02, 2013 '3-Sweep' Software Can Extract 3D Objects Out of a Single Photo With just a few mouse clicks, turn an object in a photograph into a 3D, editable creation. More 3 Sweep videos.

These simple cognitive tasks for humans are particularly difficult for automatic algorithms. Thus, our approach combines the cognitive abilities of humans with the computational accuracy of the machine to solve this problem. Our technique provides the user the means to quickly create editable 3D parts-human assistance implicitly segments a complex object into its components, and positions them in space.

In our interface, three strokes are used to generate a 3D component that snaps to the shape's outline in the photograph, where each stroke defines one dimension of the component. The computer reshapes the component to fit the image of the object in the photograph as well as to satisfy various inferred geometric constraints imposed by its global 3D structure.

We show that with this intelligent interactive modeling tool, the daunting task of object extraction is made simple. Once the 3D object has been extracted, it can be quickly edited and placed back into photos or 3D scenes, permitting object-driven photo editing tasks which are impossible to perform in image-space. We show several examples and present a user study illustrating the usefulness of our technique.

Paper: Video: Youtube: Youku: User Study:. Comparison Video:.