Technical Papers

Image-Based Reconstruction

Tuesday, 23 July 2:00 PM - 3:30 PM
Session Chair: Wojciech Matusik, Massachusetts Institute of Technology

Scene Reconstruction From High Spatio-Angular Resolution Light Fields

This paper describes an efficient method for scene reconstruction and representation of complex, detailed environments from high spatio-angular-resolution light fields.

Changil Kim
ETH Zürich, Disney Research Zürich

Henning Zimmer
ETH Zürich

Yael Pritch
Disney Research Zürich

Alexander Sorkine-Hornung
Disney Research Zürich

Markus Gross
ETH Zürich, Disney Research Zürich

Image-Based Reconstruction and Synthesis of Dense Foliage

A method for reconstructing and synthesizing dense foliage from images. Starting with point-cloud data from multi-view stereo, the method iteratively fits an exemplar leaf to the points. A statistical model of leaf shape and appearance is used to synthesize new leaves of the captured species.

Derek Bradley
Disney Research Zürich

Derek Nowrouzezahrai
Université de Montréal

Paul Beardsley
Disney Research Zürich

Dynamic Hair Manipulation in Images and Videos

This single-view hair-modeling technique for generating visually and physically plausible 3D hair models with modest user interaction enables hair manipulation in many new ways that were previously difficult with a single image, such as dynamic simulation and hair editing in videos.

Menglei Chai
Zhejiang University

Lvdi Wang
Microsoft Research Asia

Yanlin Weng
Zhejiang University

Xiaogang Jin
Zhejiang University

Kun Zhou
Zhejiang University

Structure-Aware Hair Capture

A system that reconstructs coherent and plausible wisps with awareness of the underlying hair structures from a set of images of complex hairstyle. The reconstructed wisps can synthesize hair strands that are plausible for hair simulation and animation.

Linjie Luo
Princeton University

Hao Li
University of Southern California, Industrial Light & Magic

Szymon Rusinkiewicz
Princeton University