Image Based Modeling

BA, PR, DA

Przemyslaw Musialski

Content:

Description

In image-based modeling, a static 3d object is modeled with the help of one or more images or videos. While this definition is very general, such methods are often also referred to as photogrammetric modeling, especially in the photogrammetry and remote sensing community.

Generally, in order to obtain true 3d properties of an object, the input must consist of at least two or more perspective images of the scene. There are also single-image methods which usually rely on user input or knowledge of the scene objects in order to compensate for the missing information. The outcome usually consists of medium-detail geometric models, in some cases enriched with finer detail. Some methods also deliver textures and more de- tailed geometry. The degree of user interaction varies across the methods as well. Generally, the tradeoff is between quality and scalability. More user interaction leads to more accurate models and semantics, but such approaches do not scale well to huge amounts of data. Using fully automatic methods is an option, but they are more error prone and also depend more on the quality of the input.

This topic addresses students interested in interactive image-based modeling systems which aim at the generation of high-quality geometry. Recent papers which deal with the problem are for instance (SIGGRAPH 2012): INTERACTIVE IMAGES: CUBOID PROXIES FOR SMART IMAGE MANIPULATION.

Students interested in the topic are welcome to contact me at: pm (at) cg.tuwien.ac.at

Possible Topics

Requirements

Environment