Download now Free registration required
In this paper, the authors wish to build a high quality database of images depicting scenes, along with their real-world Three-Dimensional (3D) coordinates. Such a database is useful for a variety of applications, including training systems for object detection and validation of 3D output. They build such a database from images that have been annotated with only the identity of objects and their spatial extent in images. Important for this task is the recovery of geometric information that is implicit in the object labels, such as qualtitative relationships between objects (attachment, support and occlusion) and quantitative ones (inferring camera parameters).
- Format: PDF
- Size: 1866.3 KB