Under stereo settings, the twin problems of image superresolution (SR) and high-resolution (HR) depth estimation are intertwined. The subpixel registration information required for image superresolution is tightly coupled to the 3D structure. The effects of parallax and pixel averaging (inherent in the downsampling process) preclude a priori estimation of pixel motion for superresolution. These factors also compound the correspondence problem at low resolution (LR), which in turn affects the quality of the LR depth estimates. In this paper, we propose an integrated approach to estimate the HR depth and the SR image from multiple LR stereo observations. Our results demonstrate the efficacy of the proposed method in not only being able to bring out image details but also in enhancing the HR depth over its LR counterpart. © 2010 IEEE.

A. N. Rajagopalan

Department of Electrical Engineering

3D structure

Apriori

CORRESPONDENCE PROBLEMS

Depth Estimation

DOWNSAMPLING

GRAPH CUT

High resolution

IMAGE SUPER-RESOLUTION

integrated approach

LOW RESOLUTION

Markov Random Fields

Resolution enhancement

SUBPIXEL REGISTRATION

Super resolution

TIGHTLY-COUPLED

Geometrical optics

image segmentation

Optical resolving power

Pixels

Visibility

three dimensional

Algorithm

article

Artificial Intelligence

automated pattern recognition

computer assisted diagnosis

image enhancement

Image subtraction

methodology

Photography

reproducibility

Sensitivity and Specificity

signal processing

three dimensional imaging

Algorithms

Image Interpretation, Computer-Assisted

Imaging, Three-Dimensional

Pattern Recognition, Automated

Photogrammetry

Reproducibility of Results

Signal Processing, Computer-Assisted

SUBTRACTION TECHNIQUE

IIT Madras is a public technical and research university located in Chennai, Tamil Nadu. Founded in 1959, it is recognised as an Institute of National Importance.

IIT Madras has been ranked as the top engineering institute in India for four years in a row by the National Institutional Ranking Framework of the MHRD

It currently offers undergraduate, postgraduate and research degrees across 16 disciplines in Engineering, Sciences, Humanities and Management. About 596 faculty belonging to science and engineering departments and centres of the Institute are engaged in teaching, research and industrial consultancy.

IIT Madras

Resolution Enhancement in Multi-Image Stereo

IEEE Transactions on Pattern Analysis and Machine Intelligence

We address the problem of estimating the latent high-resolution (HR) image of a 3D scene from a set of non-uniformly motion blurred low-resolution (LR) images captured in the burst mode using a hand-held camera. Existing blind super-resolution (SR) techniques that account for motion blur are restricted to fronto-parallel planar scenes. We initially develop an SR motion blur model to explain the image formation process in 3D scenes. We then use this model to solve for the three unknowns - the camera trajectories, the depth map of the scene, and the latent HR image. We first compute the global HR camera motion corresponding to each LR observation from patches lying on a reference depth layer in the input images. Using the estimated trajectories, we compute the latent HR image and the underlying depth map iteratively using an alternating minimization framework. Experiments on synthetic and real data reveal that our proposed method outperforms the state-of-the-art techniques by a significant margin. © 1992-2012 IEEE.

IEEE Transactions on Image Processing

Multi-image blind super-resolution of 3D scenes

Superresolution is the process of combining information from multiple subpixel-shifted low-resolution images to form a high-resolution image. It works quite well under ideal conditions but deteriorates rapidly with inaccuracies in motion estimates. We model the original high-resolution image as a Markov random field (MRF) with a discontinuity adaptive regularizer. Given the low-resolution observations, an estimate of the superresolved image is obtained by using the iterated conditional modes (ICM) algorithm, which maximizes the local posterior conditional probability sequentially. The proposed method not only preserves edges but also lends robustness to errors in the estimates of motion and blur parameters. We derive theoretically the neighborhood structure for the posterior distribution in the presence of warping, blurring, and downsampling operations and use this to effectively reduce the overall computations. Results are given on synthetic as well as real data to validate our method. © 2007 Optical Society of America.

Fulltext

Journal of the Optical Society of America A: Optics and Image Science, and Vision

Robust and computationally efficient superresolution algorithm

Signal Processing: Image Communication

Stereoscopic 3D from 2D video with super-resolution capability

Sixth International Conference on 3-D Digital Imaging and Modeling (3DIM 2007)

Super-Resolution Stereo- and Multi-View Synthesis from Monocular Video Sequences

Approximate Labeling via Graph Cuts Based on Linear Programming

Minimizing Nonsubmodular Functions with Graph Cuts-A Review

Resolution enhancement in multi-image stereo

Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
ISSN	01628828
Open Access	No