A Convex Solution to Disparity Estimation from Light Fields via the Primal-Dual Method

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Linear-Quadratic-Gaussian (LQG) control is a fundamental control paradigm that is studied in various fields such as engineering, computer science, economics, and neuroscience. It involves controlling a system with linear dynamics and imperfect observations ...

Within the context of contemporary machine learning problems, efficiency of optimization process depends on the properties of the model and the nature of the data available, which poses a significant problem as the complexity of either increases ad infinit ...

The invention relates to a microfluidic device (3) comprising: - an inlet channel (31) having an inlet configured to be operatively connected with a droplet source (2) wherein the inlet channel (31) has a width wi and height hi; and - an outlet channel wit ...

Herein described are diaryl ether compounds having the structure (I) as well as a method for their manufacture from lignin. ...

Exploring a wide range of design options is crucial for every sound conceptual design process. In the conventional structural design workflow, optimization techniques are generally employed to generate well-performing design options. However, focusing only ...

Control design for robotic systems is complex and often requires solving an optimization to follow a trajectory accurately. Online optimization approaches like Model Predictive Control (MPC) have been shown to achieve great tracking performance, but requir ...

An electroadhesive gripping system and a method for gripping and manipulating an object are disclosed. The invention provides a novel approach particularly useful to pick fabrics or otherwise flat and flexible objects including a method relying on electroa ...

Integrating various reinforcements into 3D concrete printing (3DCP) is an efficient method to satisfy critical requirements for structural applications. This paper explores an explainable ensemble machine learning (EML) method to predict the bond failure m ...

We present an end-to-end trainable Neural Network architecture for stereo imaging that jointly locates and estimates human body poses in 3D. Our method defines a 2D pose for each human in a stereo pair of images and uses a correlation layer with a composit ...

Learning to embed data into a space where similar points are together and dissimilar points are far apart is a challenging machine learning problem. In this dissertation we study two learning scenarios that arise in the context of learning embeddings and o ...

A Convex Solution to Disparity Estimation from Light Fields via the Primal-Dual Method

Chat with Graph Search

Distributionally Robust Linear Quadratic Control

Universal and adaptive methods for robust stochastic optimization

Microfluidic device for sample encapsulation and method for operation thereof

Diaryl ether compound and manufacturing method from lignin

Computational conceptual design — typological exploration of spatial truss systems through optimization

Training Efficient Controllers via Analytic Policy Gradient

Electroadhesive gripping system and method for gripping an object

Reinforcement bond performance in 3D concrete printing: Explainable ensemble learning augmented by deep generative adversarial networks

Joint Human Pose Estimation and Stereo 3D Localization

Learning embeddings: efficient algorithms and applications