Guided Image Super-Resolution: A New Technique for Photogeometric Super-Resolution in Hybrid 3-D Range Imaging

  title={Guided Image Super-Resolution: A New Technique for Photogeometric Super-Resolution in Hybrid 3-D Range Imaging},
  author={Florin C. Ghesu and Thomas K{\"o}hler and Sven Haase and Joachim Hornegger},
In this paper, we augment multi-frame super-resolution with the concept of guided filtering for simultaneous upsampling of 3-D range data and complementary photometric information in hybrid range imaging. Our guided super-resolution algorithm is formulated as joint maximum a-posteriori estimation to reconstruct high-resolution range and photometric data. In order to exploit local correlations between both modalities, guided filtering is employed for regularization of the proposed joint energy… 
Robust Multiframe Super-Resolution Employing Iteratively Re-Weighted Minimization
This paper proposes spatially adaptive Bayesian modeling and an iterative algorithm for robust super-resolution imaging and introduces a weighted Gaussian observation model to consider space variant noise and weighted bilateral total variation to exploit sparsity of natural images.
A Unified Bayesian Approach to Multi-Frame Super-Resolution and Single-Image Upsampling in Multi-Sensor Imaging
This paper proposes a unified method for single-image upsampling and multi-frame super-resolution of multi-channel images using a Bayesian model formulated by a novel image prior to exploit sparsity of individual channels as well as a locally linear regression between the complementary channels.
Multi-Frame Super-Resolution Reconstruction with Applications to Medical Imaging
This work introduces novel multi-sensor super-resolution techniques and investigates two complementary problem statements, and introduces a reconstruction algorithm that exploits guidance data for motion estimation, feature driven adaptive regularization, and outlier detection to reliably super-resolve a second modality.
Binarization Driven Blind Deconvolution for Document Image Restoration
A novel binarization driven blind deconvolution approach to couple both tasks in a common framework derived as an energy minimization problem regularized by a novel consistency term to exploit textbinarization as a prior for blind deconVolution.


Fast and robust multiframe super resolution
This paper proposes an alternate approach using L/sub 1/ norm minimization and robust regularization based on a bilateral prior to deal with different data and noise models and demonstrates its superiority to other super-resolution methods.
Resolution Enhancement of PMD Range Maps
This work follows a Bayesian framework by modeling the original HR range as a Markov random field (MRF) and proposes the use of an edge-adaptive MRF prior to handle discontinuities.
Range map superresolution-inpainting, and reconstruction from sparse data
ToF Meets RGB: Novel Multi-Sensor Super-Resolution for Hybrid 3-D Endoscopy
This paper proposes a novel multi-frame super-resolution framework to improve range images in a ToF/RGB multi-sensor setup that exploits high-resolution RGB data to estimate subpixel motion used as a cue for range super- resolution.
Variational Bayesian Super Resolution
This paper addresses the super resolution (SR) problem from a set of degraded low resolution (LR) images to obtain a high resolution (HR) image and proposes novel super resolution methods where the HR image and the motion parameters are estimated simultaneously.
High-quality scanning using time-of-flight depth superresolution
It is shown that ideas from traditional color image superresolution can be applied to TOF cameras in order to obtain 3D data of higher X-Y resolution and less noise.
A Weighted Optimization Approach to Time-of-Flight Sensor Fusion
Object and subjective results proof the suitability of the approach to time-of-flight super resolution approach for depth scenery capture, based on the combination of depth and texture sources.
LidarBoost: Depth superresolution for ToF 3D shape scanning
LidarBoost is presented, a 3D depth superresolution method that combines several low resolution noisy depth images of a static scene from slightly displaced viewpoints, and merges them into a high-resolution depth image.
Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images
A hybrid method combining the simplicity of theML and the incorporation of nonellipsoid constraints is presented, giving improved restoration performance, compared with the ML and the POCS approaches.
Advances and challenges in super‐resolution
A detailed study of several very important aspects of Super‐Resolution, often ignored in the literature, are presented, and robustness, treatment of color, and dynamic operation modes are discussed.