Sema Berkiten will present her Pre FPO on Monday, February 8, 2016 at 10:00am in CS 401. The members of her committee are: Szymon Rusinkiewicz (adviser), Adam Finkelstein (reader), Hao Li (USC, reader), Thomas Funkhouser (non-reader) and David Dobkin (non-reader). Title: Capturing, Processing, and Synthesizing Surfaces with Details Abstract: Geometry acquisition has become increasingly popular in computer graphics and vision, with demand for high-quality models driven by advances in 3D printing, realistic real-time renderings of 3D characters in video games, digital libraries for historical objects etc. In this thesis, we focus on techniques to produce and process detailed geometry including acquisition of real world objects, processing and combining the captured data, and synthesizing new surfaces from existing ones. First, we summarize a 2D acquisition technique called photometric stereo to capture high resolution surface details. As a validation step, we solve a misalignment problem for photometric datasets which may be caused by perturbations to the camera or to the object, or the effect of optical image stabilization, especially in long photo shoots. After the dataset is validated, the surface normals can be computed using one of the photometric stereo algorithms. In order to decide which algorithm to use, we present a synthetic photometric benchmark to evaluate various algorithms for different scenarios. Next, we introduce a semi-automated system to convert photometric datasets into geometry-aware non-photorealistic illustrations of surface details that obey the common conventions of epigraphy (black-and-white archaeological drawings of inscriptions). This system is composed of rectification of the surface normals to correct camera perspective, segmentation of the inscriptions from the background, classification of the inscription based on carving technique (either slightly deeper grooves, or shallow pecked-out regions), and stylization of the inscriptions in various styles. To produce a detailed surface in 3D, we propose an approach to combine a rough 3D geometry with fine detailed normal maps obtained from different views. We begin with unaligned 2D normal maps and a rough 3D geometry, and automatically optimize the alignments through a two-step iterative registration algorithm to align each normal map to the 3D geometry. We then map the normals onto the surface, correct and seamlessly blend them together. At the end, we optimize the geometry to produce a high-quality 3D model that incorporates the high-frequency details from the normal maps. Finally, we present an algorithm for realistically transferring surface details (specifically, displacement maps) from existing high-quality 3D models to simple shapes that may be created with easy-to-learn modeling tools. Our key insight is to use metric learning to find a combination of geometric features that successfully predicts detail-map similarities on the source mesh, and use the learned feature combination to drive the detail transfer.