Home

Publications

Projects

Bio

Art

Capturing, Processing, and Synthesizing Surfaces with Details

Sema Berkiten, PhD Thesis, Princeton University, July 2016.

Summary: This thesis focuses on techniques to produce and process detailed geometry including acquisition of real world objects, processing and fusing the captured data, and synthesizing new surfaces from existing ones.

Learning Detail Transfer based on Geometric Features

Ongoing...

Semi-Automatic Digital Epigraphy from Images with Normals

Sema Berkiten, Xinyi Fan, and Szymon Rusinkiewicz, International Symposium on Non-Photorealistic Animation and Rendering (NPAR), June 2015.

Summary: A semi-automated system for converting photometric datasets (RGB images with normals) into geometry-aware non-photorealistic illustrations that obey the common conventions of epigraphy (black-and-white archaeological drawings of inscriptions).

Merge2-3D: Combining Multiple Normal Maps with 3D Surfaces

Sema Berkiten, Xinyi Fan, and Szymon Rusinkiewicz, International Conference on 3D Vision (3DV), December 2014.

Summary: Enhancing rough 3D geometry with fine details obtained from unaligned multiple normal maps.

An RGBN Benchmark

Sema Berkiten and Szymon Rusinkiewicz, Technical Report, Princeton Univeristy.

Summary: A synthetic photometric benchmark for applications such as photometric stereo.

Alignment of Images Captured Under Different Light Directions

Sema Berkiten and Szymon Rusinkiewicz, Technical Report, Princeton University, July, 2014.

Summary: Alignment of photometric datasets (images of the same object which are captured from a fixed camera position, under different lighting directions).

A Pointwise Correspondence Based DT-MRI Fiber Similarity Measure

Sema Berkiten and Burak Acar, Proc. 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Buenos Aires, Argentina, IEEE, 2010.

Summary: Clustering 3D Diffusion Tensor Magnetic Resonance Imaging (DT-MRI) fibers.