MaSuperResDepth

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Super Resolution Depth Maps

Supervision: Christian Rupprecht, Federico Tombari

This project aims at single image super-resolution applied to depth maps. Many available depth sensors have a relatively low resolution compared to the accompanied color image. We would like to recover a high-resolution depth map from the combination of low-res depth and high-res RGB image. This problem is inherently ill-posed since a multiplicity of solutions exist for any given input. Nonetheless it is a highly studies topic in computer vision. Starting with the work of Dong et. al. "Image Super-Resolution Using Deep Convolutional Networks" (TPAMI 2015) we would like to expore the application of deep neural networks to this field of study.


For further information please contact: Christian Rupprecht

ProjectForm
Title: Super Resolution Depth Maps
Abstract: This project aims at single image super-resolution applied to depth maps. Many available depth sensors have a relatively low resolution compared to the accompanied color image. We would like to recover a high-resolution depth map from the combination of low-res depth and high-res RGB image. This problem is inherently ill-posed since a multiplicity of solutions exist for any given input. Nonetheless it is a highly studies topic in computer vision. Starting with the work of Dong et. al. "Image Super-Resolution Using Deep Convolutional Networks" (TPAMI 2015) we would like to expore the application of deep neural networks to this field of study.
Student:  
Director: Prof. Nassir Navab
Supervisor: Christian Rupprecht, Federico Tombari
Type: DA/MA/BA
Area:  
Status: draft
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.2 - 17 Jan 2017 - 10:34 - ChristianRupprecht