Training-based method for low-level vision problems

A Primal Dual Network for Low-Level Vision Problems

In the past, classic energy optimization techniques were the driving force in many innovations and are a building block for almost any problem in computer vision. Efficient algorithms are mandatory to achieve real-time processing, needed in many applications like autonomous driving. However, energy models even if designed by human experts might never be able to fully capture the complexity of n...

Learning Low-level Vision Learning Low-level Vision

We show 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. We model that world with a Markov network, learning the network parameters from the examples. Bayesian belief propagation allows us to e ciently nd a local maximum of the posterior probability for the scene, given the image...

Low-level global features for vision-based localizations

Vision-based self-localization is the ability to derive one’s own location from visual input only without knowledge of a previous position or idiothetic information. It is often assumed that the visual mechanisms and invariance properties used for object recognition will also be helpful for localization. Here we show that this is neither logically reasonable nor empirically supported. We argue ...

Modular Integration for Low-level and High-level Vision Problems in a Multiresolution Framework

Unifying Low-Level Vision

This white paper supports the goal of establishing Computer Vision as a coherent intellectual discipline by suggesting a specific agenda for the unification of many low-level vision principles, algorithms, and data structures. Our goal is to identify a set of highly related low-level vision problems, define their common structure, and establish a coherent intellectual discipline around the shar...