3D Depth From a Single Photograph | Two Minute Papers #54

Subscribers:
1,720,000
Published on ● Video Link: https://www.youtube.com/watch?v=ZolWxY4f9wc



Duration: 2:07
18,718 views
343


This piece of work tries to estimate depth information from an input photogaph. This means that it looks at the photo and tries to tell how far away parts of the image are from the camera, and the final goal is that we provide a photograph for which the depth information is completely unknown and we ask the algorithm to provide it for us.

_______________________________

The paper "3-D Depth Reconstruction from a Single Still Image" is available here:
http://www.cs.cornell.edu/~asaxena/learningdepth/saxena_ijcv07_learningdepth.pdf

The source of the shown video at the end:
https://www.youtube.com/watch?v=GWWIn29ZV4Q

WE WOULD LIKE TO THANK OUR GENEROUS SUPPORTERS WHO MAKE TWO MINUTE PAPERS POSSIBLE:
Sunil Kim, Vinay S.

Subscribe if you would like to see more of these! - http://www.youtube.com/subscription_center?add_user=keeroyz

The thumbnail image background was created by Willy Verhulst (CC BY 2.0) - https://flic.kr/p/pZj8KD
Splash screen/thumbnail design: Felícia Fehér - http://felicia.hu

Károly Zsolnai-Fehér's links:
Patreon → https://www.patreon.com/TwoMinutePapers
Facebook → https://www.facebook.com/TwoMinutePapers/
Twitter → https://twitter.com/karoly_zsolnai
Web → https://cg.tuwien.ac.at/~zsolnai/







Tags:
two minute papers
3-D Depth Reconstruction from a Single Still Image
depth from photograph
deep photograph
deep images
3d model from photo
3d model from image
depth from image
Monocular vision
Learning depth
3D reconstruction
Dense reconstruction
Markov random field
Depth estimation
Monocular depth
Stereo vision
Hand-held camera
Visual modeling