Shadow removal is an important problem for both artists and algorithms. Previous methods handle some shadows well but, because they rely on the shadowed data, perform poorly in cases with severe degradation. Image-completion algorithms can completely replace severely degraded shadowed regions, and perform well with smaller-scale textures, but often fail to reproduce larger-scale macrostructure that may still be visible in the shadowed region. This paper provides a general framework that leverages degraded (e.g., shadowed) data to guide the image completion process by extending the objective function commonly used in current state-of-the-art image completion energy-minimization methods. This approach achieves realistic shadow removal even in cases of severe degradation and could be extended to other types of localized degradation.

Approximate Nearest-Neighbour Field (ANNF\ maps between two related images are commonly used by computer vision and graphics community for image editing, completion, retargetting and denoising. In this work we generalize ANNF computation to unrelated image pairs. For accurate ANNF map computation we propose Feature Match, in which the low-dimensional features approximate image patches along with global colour adaptation. Unlike existing approaches, the proposed algorithm does not assume any relation between image pairs and thus generalises ANNF maps to any unrelated image pairs. This generalization enables ANNF approach to handle a wider range of vision applications more efficiently. The following is a brief description of the applications developed using the proposed Feature Match framework. The first application addresses the problem of detecting the optic disk from retinal images. The combination of ANNF maps and salient properties of optic disks leads to an efficient optic disk detector that does not require tedious training or parameter tuning. The proposed approach is evaluated on many publicly available datasets and an average detection accuracy of 99% is achieved with computation time of 0.2s per image. The second application aims to super-resolve a given synthetic image using a single source image as dictionary, avoiding the expensive training involved in conventional approaches. In the third application, we make use of ANNF maps to accurately propagate labels across video for segmenting video objects. The proposed approach outperforms the state-of-the-art on the widely used benchmark SegTrack dataset. In the fourth application, ANNF maps obtained between two consecutive frames of video are enhanced for estimating sub-pixel accurate optical flow, a critical step in many vision applications. Finally a summary of the framework for various possible applications like image encryption, scene segmentation etc. is provided.

This thesis introduces methods for adding user-guided depth-aware effects to images captured with a consumer-grade stereo camera with minimal user interaction. In particular, we present methods for highlighted depth-of-field, haze, depth-of-field, and image relighting. Unlike many prior methods for adding such effects, we do not assume prior scene models or require extensive user guidance to create such models, nor do we assume multiple input images. We also do not require specialized camera rigs or other equipment such as light-field camera arrays, active lighting, etc. Instead, we use only an easily portable and affordable consumer-grade stereo camera. The depth is calculated from a stereo image pair using an extended version of PatchMatch Stereo designed to compute not only image disparities but also normals for visible surfaces. We also introduce a pipeline for rendering multiple effects in the order they would occur physically. Each can be added, removed, or adjusted in the pipeline without having to reapply subsequent effects. Individually or in combination, these effects can be used to enhance the sense of depth or structure in images and provide increased artistic control. Our interface also allows editing the stereo pair together in a fashion that preserves stereo consistency, or the effects can be applied to a single image only, thus leveraging the advantages of stereo acquisition even to produce a single photograph.