Changchang Wu



Home   |   Publications    |   Research   |  Code  VisualSFM

I work for Google now, trying to develop exciting products using 3D computer vision. I received my PhD in computer science from UNC Chapel Hill, under the supervision of Marc Pollefeys and Jan-Michael Frahm. After graduation, I have worked as a postdoc with Steve Seitz and Brian Curless at University of Washington.

My research interests include 3D reconstruction, feature detection, and GPGPU for Computer Vision. Here is my resume.

News! my paper "critical configurations for radial distortion self- calibration" is accepted as oral by CVPR 2014.


VisualSFM : A Visual Structure From Motion System

A Visual 3D reconstruction system that integrates SiftGPU and Multicore Bundle Adjustment. It is easy to use with a feature-packed GUI. Check out my 3DV2013 paper for more algorithmic details: "Towards Linear-time Incremental Structure from Motion", (webpage, supplemental, video)


Open-source Softwares for SfM

Multicore Bundle Adjustment, optimized for both GPU and CPU.

SIFT on GPU (SiftGPU), works for nVidia, ATI and Intel cards.