This paper presents new techniques for improving the structural quality of automatically acquired architectural 3D models. Common architectural features like parallelism and ortho...
We present a system that constructs "implicit shape models" for classes of rigid 3D objects and utilizes these models to estimating the pose of class instances in single...
—Color models are often used for representing object appearance for foreground segmentation applications. The relationships between colors can be just as useful for object select...
This paper investigates the use of the Bayesian inference for devising an example-based rendering procedure. As prior model of this Bayesian inference, we exploit the multiscale n...
We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the e...
Erik B. Sudderth, Antonio B. Torralba, William T. ...