Visualizing and manipulating volumetric data is a major component in many areas including anatomical registration in biomedical fields, seismic data analysis in the oil industry, machine part design in computer-aided geometric design, character animation in the movie industry, and fluid simulation. These industries have to meet the demands of the times and be able to make meaningful assertions about the data they generate. The shear size of this data presents many challenges to facilitating realtime interaction. In the recent decade, graphics hardware has become increasingly powerful and more sophisticated which has introduced a new realm of possibilities for processing volumetric data. This thesis focuses on a suite of techniques for viewing and editing volumetric data that efficiently use the processing power of central processing units (CPUs) as well as the large processing power of the graphics hardware (GPUs). This work begins with an algorithm to improve the efficiency of a texture-based volume rendering. We continue with a framework for performing realtime constructive solid geometry (CSG) with complex shapes and smoothing operations on watertight meshes based on a variation of Depth Peeling. We then move to an intuitive technique for deforming volumetric data using a collection of control points. Finally, we apply this technique to image registration of 3-dimensional computed tomography (CT) images used for lung cancel treatment, planning.

Morphable guidelines are a 3D structure that helps users achieve better face warping on 2D portrait images. Faces can be difficult to warp accurately because the rotation of the head affects the shape of the facial features. I bypass the problem by utilizing the popular Loomis ‘ball and plane’ head drawing guideline as a proxy structure. The resulting ‘morphable guidelines’ consist of a simple 3D head model that can be reshaped by the user and aligned to their input image. The vertices of the model go on to act as deformation points for a 2D image deformation algorithm. Thus, the user can seamlessly transform the face proportions in the 2D image by transforming the proportions of the morphable guidelines. This system can be used for both retouching and caricature warping purposes, as it is well-suited for both subtle and extreme modifications. This system is advantageous over previous work in face warping because our morphable guidelines can be used on a wide range of head orientations and do not require the generation of a full 3D model. / Graduate / 0984 / syugao@gmail.com

Nonrigid deformation modeling and estimation from images is a technically challenging task due to its nonlinear, nonconvex and high-dimensional nature. Traditional optimization procedures often rely on good initializations and give locally optimal solutions. On the other hand, learning-based methods that directly model the relationship between deformed images and their parameters either cannot handle complicated forms of mapping, or suffer from the Nyquist Limit and the curse of dimensionality due to high degrees of freedom in the deformation space. In particular, to achieve a worst-case guarantee of ∈ error for a deformation with d degrees of freedom, the sample complexity required is O(1/∈d). In this thesis, a generative model for deformation is established and analyzed using a unified theoretical framework. Based on the framework, three algorithms, Data-Driven Descent, Top-down and Bottom-up Hierarchical Models, are designed and constructed to solve the generative model. Under Lipschitz conditions that rule out unsolvable cases (e.g., deformation of a blank image), all algorithms achieve globally optimal solutions to the specific generative model. The sample complexity of these methods is substantially lower than that of learning-based approaches, which are agnostic to deformation modeling. To achieve global optimality guarantees with lower sample complexity, the structureembedded in the deformation model is exploited. In particular, Data-driven Descentrelates two deformed images that are far away in the parameter space by compositionalstructures of deformation and reduce the sample complexity to O(Cd log 1/∈).Top-down Hierarchical Model factorizes the local deformation into patches once theglobal deformation has been estimated approximately and further reduce the samplecomplexity to O(Cd/1+C2 log 1/∈). Finally, the Bottom-up Hierarchical Model buildsrepresentations that are invariant to local deformation. With the representations, theglobal deformation can be estimated independently of local deformation, reducingthe sample complexity to O((C/∈)d0) (d0 ≪ d). From the analysis, this thesis showsthe connections between approaches that are traditionally considered to be of verydifferent nature. New theoretical conjectures on approaches like Deep Learning, arealso provided. practice, broad applications of the proposed approaches have also been demonstrated to estimate water distortion, air turbulence, cloth deformation and human pose with state-of-the-art results. Some approaches even achieve near real-time performance. Finally, application-dependent physics-based models are built with good performance in document rectification and scene depth recovery in turbulent media.