New 3D Reconstruction Algorithm from UC San Diego

Augmented reality walkthroughs of a building or a city, online alignment of a camera network and 3D navigation through a collection of photographs are just a few of the potential applications of an algorithm created in the computer science department at UC San Diego's Jacobs School of Engineering.

For this work, UCSD computer scientists earned was one of three honorable mentions for the David Marr prize which is the best paper award at the world's premier computer vision conferences, ICCV, the International Conference on Computer Vision which took place last month in Rio de Janeiro, Brazil.

"The algorithm is very much practical. We have performed real-life 3D reconstructions. In fact, the significance of the paper lies in our approaches for designing a theoretically correct algorithm that also works well in practice," explained Manmohan Chandraker, the first author on the award-winning ICCV paper and a fifth-year Ph.D. student in the Department of Computer Science and Engineering at UCSD's Jacobs School of Engineering.

Category:

Science & Technology

Tags:

• computer
• science
• algorithm
• math
• geometry
• movies
• vision
• robots
• cameras
• video

[abcvwecv]

Pretty cool! solves some interesting theoretical problems.

[cankarales]

lol'd @ his english lango skills :D

[DanFrederiksen]

well I said it in jest thinking it was merely a poor video editing issue but turns out the algorithm is not for 3d reconstruction at all. just computing where the cameras were given human pinpointed correlating points in the images. harshly speaking.. that's useless. unimpressive. not at all the same as 3d reconstruction

[DanFrederiksen]

why not show us the reconstructed Taj Mahal!!!!

an F! : )

[robodrishti]

have you heard of photsynth?

[plooky123]

awesome !