Egon C. Pasztor

Learn More
The Problem: Pixel representations for images do not have resolution independence. When we zoom into a bitmapped image, we get a blurred image. Figure 1 shows the problem for a teapot image, rich with real-world detail. We know the teapot’s features should remain sharp as we zoom in on them, yet standard pixel interpolation methods, such as pixel(More)
We describe a learning-based method for low-level vision problems—estimating scenes from images. We generate a synthetic world of scenes and their corresponding rendered images, modeling their relationships with a Markov network. Bayesian belief propagation allows us to efficiently find a local maximum of the posterior probability for the scene, given an(More)
The Hyperscore graphical computer-assisted composition system for users with limited or no musical training takes freehand drawing as input, letting users literally sketch their pieces. Designing an intelligent, intuitive system that enables novices-particularly children-to compose music is a difficult task. We can view the problem as a spectrum of tasks(More)
We seek the scene interpretation that best explains image data. For example, we may want to infer the projected velocities (scene) which best explain two consecutive image frames (image). From synthetic data, we model the relationship between image and scene patches, and between a scene patch and neighboring scene patches. Given a new image, we propagate(More)
We seek a learning-based algorithm that applies to various low-level vision problems. For each problem, we want to find the scene interpretation that best explains image data. For example, we may want to infer the projected velocities (scene) which best explain two consecutive image frames (image). From synthetic data, we model the relationship between(More)
We address the super-resolution problem: how to estimate missing high spatial frequency components of a static image. From a training set of fulland lowresolution images, we build a database of patches of corrsponding highand low-frequency image information. Given a new low-resolution image to enhance, we select from the training data a set of 10 candidate(More)
We present an example-based system for translating line drawings into different styles. The system is given a training set of many different lines, each drawn by an artist in various styles, which is used to translate new lines made by a user into a particular desired style with a it K-nearest neighbor algorithm. This algorithm fits each input line as a(More)
Perspective correction is vital for architecture photography, where it is desirable to maintain parallel vertical lines even when the view direction is angled up from the horizontal, as is the case, for example, in photographing a tall building from ground level. Vertical lines converge when they are not parallel to the film plane. This effect is not(More)