If you missed SIGGRAPH 2017 watch a selection of recorded Live Streaming Sessions.
Reconstructing 3D Surfaces From Points, Lines, Images & Water
If you missed SIGGRAPH 2017 watch a selection of recorded Live Streaming Sessions.
A method to interactively reconstruct a surface from unstructured point clouds during a scanning session. It does not use intermediate representations such as volumetric functions and produces high-quality output.
Nico Schertler
New York University, Technische Universität Dresden
Marco Tarini
Università dell'Insubria, Varese
Wenzel Jakob
École Polytechnique Fédérale de Lausanne
Misha Kazhdan
The Johns Hopkins University
Stefan Gumhold
Technische Universität Dresden
Daniele Panozzo
New York University
Introducing an algorithm for reconstructing multi-labeled material interfaces that allows the user to explicitly prescribe the topology of individual labels.
Zhiyang Huang
Washington University in St. Louis
Ming Zou
Washington University in St. Louis
Nathan Carr
Adobe Research
Tao Ju
Washington University in St. Louis
At the core of this novel, real-time, end-to-end reconstruction algorithm is a robust pose-estimation strategy that optimizes per frame for a global set of camera poses. The method removes the heavy reliance on temporal tracking and continually localizes to the globally optimized frames instead.
Angela Dai
Stanford University
Matthias Nießner
Stanford University
Michael Zollhöfer
Max-Planck-Institut für Informatik
Shahram Izadi
perceptiveIO, Inc
Christian Theobalt
Max-Planck-Institut für Informatik
This paper presents a benchmark for image-based 3D reconstruction. The benchmark sequences were acquired outside the lab, in realistic conditions. The results point to exciting challenges and opportunities for future work.
Arno Knapitsch
Intel Labs
Jaesik Park
Intel Labs
Qian-Yi Zhou
Intel Labs
Vladlen Koltun
Intel Labs
This paper presents a 3D acquisition and reconstruction method based on Archimedes submerged-volume equality. It employs fluid displacement as the shape sensor. The liquid has no line-of-sight. It penetrates cavities and hidden parts, as well as transparent and glossy materials, thus bypassing the visibility and optical limitations of scanning devices.
Kfir Aberman
Tel Aviv University, Advanced Innovation Center for Future Visual Entertainment
Oren Katzir
Tel Aviv University, Advanced Innovation Center for Future Visual Entertainment
Qiang Zhou
Shandong University
Zegang Luo
Shandong University
Andrei Sharf
Advanced Innovation Center for Future Visual Entertainment, Ben-Gurion University of the Negev
Chen Greif
The University of British Columbia
Baoquan Chen
Shandong University
Daniel Cohen-Or
Tel-Aviv University
