3-Sweep: Extracting Editable Objects from a Single Photo

Tao Chen1,2,3 ,Zhe Zhu1, Ariel Shamir3, Shi-Min Hu1, Daniel Cohen-Or2

1TNList, Department of Computer Science and Technology, Tsinghua University

2Tel Aviv University 3The Interdisciplinary Center

 

3-Sweep Object Extraction. (a) Input image. (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. 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: [PDF 5.7M]
Video: [MP4 39.5M]

Youtube:URL Youku:URL

User Study : [PDF 3.2M].
Comparison Video : [MP4 9.3M].

Software : Download Page.

Results: