Technical Papers

Surface Reconstruction

Wednesday, 24 July 2:00 PM - 3:30 PM
Session Chair: Richard Zhang, Simon Fraser University

Screened Poisson-Surface Reconstruction

This method improves Poisson-surface reconstruction by explicitly incorporating the input points as interpolation constraints. Several algorithmic improvements reduce the time complexity of the multi-resolution solver to linear.

Michael Kazhdan
The Johns Hopkins University

Hugues Hoppe
Microsoft Research

A Benchmark for Surface Reconstruction

A method for measuring surface reconstruction error in approximating reconstruction algorithms through realistically simulating imperfections of scanned surface data.

Matthew Berger
University of Utah

Joshua A. Levine
Clemson University

Luis Gustavo Nonato
Universidade de São Paulo

Gabriel Taubin
Brown University

Claudio T. Silva
Polytechnic Institute of New York University

Dense Scene Reconstruction With Points of Interest

An approach to detailed reconstruction of complex real-world scenes with a hand-held range camera. The user moves the camera through the environment. A registration and integration pipeline produces a detailed scene model. The results demonstrate that detailed reconstructions of complex scenes can be obtained with a commodity camera.

Qian-Yi Zhou
Stanford University

Vladlen Koltun
Stanford University

Scalable Real-Time Volumetric Surface Reconstruction

A memory-efficient, streamable, hierarchical GPU data structure for 3D reconstruction of large-scale scenes with fine geometric details in real time. The system fuses live depth maps from a moving Kinect camera to generate high-quality 3D models of unbounded size.

Jiawen Chen
Microsoft Research Cambridge

Dennis Bautembach
Microsoft Research Cambridge

Shahram Izadi
Microsoft Research Cambridge