Data-Driven is on the way!

  • Flickr: > 1.7 million photos / day
  • Facebook: > 30 million photos / day
  • YouTube: > 20 hours of video every minute

Exploiting online photo collections – large and keep-growing data set!

1. Organizing and visualizing photos and scenes

  • Photo Tourism – S. Seitz, R. Szeliski http://phototour.cs.washington.edu/
  • Towards Internet-scale Multi-view Stereo, Furukawa, et al., CVPR 2010
  • PhotoSynth
  • Exploring virtual spaces – Creating and exploring a large photorealistic virtual space, Sivic et al., Workshop on Internet Vision 2008.

2. Image enhencement

  • Scene Completion using Millions of Photographs,Hays and Efros, SIGGRAPH 2007, with Gist scene descriptor (Oliva and Torralba 2001)
  • Photo Clip Art, Lalonde et al., SIGGRAPH 2007
  • Intrinsic Colorization, Liu et al., SIGGRAPH Asia 2008
  • Sketch2Photo: Internet Image Montage, Chen et al., SIGGRAPH Asia 2009
  • Deep Photo: Model-Based Photograph Enhancement and Viewing, Kopf et al., SIGGRAPH Asia 2008
  • Bing Maps 3D

3. Understanding people, places, and cameras

  • Mapping the World’s Photos, Crandall et al., WWW 2009
  • Priors for Large Photo Collections and What They Reveal about Cameras, S. Kuthirummal, A. Agarwala, D. B Goldman, and S. K. Nayar, ECCV 2008

4. How large is “sufficiently large”?

“Indeed, our initial experiments with the gist descriptor on a dataset of ten thousand images were very discouraging. However, increasing the image collection to two million yielded a qualitative leap in performance…”

-80 million tiny images: a large dataset for non-parametric object and scene recognition, A. Torralba, R. Fergus, W. T. Freeman, PAMI 2008
5. “Brute-force Image Understanding”

“Instead of trying to manipulate the object to change its orientation, color distribution, etc. to fit the new image, we simply retrieve an object of a specified class that has all the required properties (camera pose, lighting, resolution, etc) from our large object library.” Photo Clip Art, Lalonde et al., SIGGRAPH 2007

6. Law of Large Image Collections

“Given a sufficiently large corpus of images, with high probability there exists an image similar to the one you are looking for.”

  1. Vision algorithms are starting to be robust enough to work on large-scale Internet photo collections
  2. Law of large photo collections can make some hard problems easier
  3. Statistics of large photo collections reveal useful information about people, places, and cameras
Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

生活在西班牙

自己动手丰衣足食

BlueAsteroid

Just another WordPress.com site

Jing's Blog

Just another WordPress.com site

Start from here......

我的心情魔方

天才遠私廚

希望能做一個分享各種資訊的好地方

语义噪声

西瓜大丸子汤的博客

笑对人生,傲立寰宇

Just another WordPress.com site

Where On Earth Is Waldo?

A Project By Melanie Coles

the Serious Computer Vision Blog

A blog about computer vision and serious stuff

Cauthy's Blog

paper review...

Cornell Computer Vision Seminar Blog

Blog for CS 7670 - Special Topics in Computer Vision

datarazzi

Life through nerd-colored glasses

Luciana Haill

Brainwaves Augmenting Consciousness

槑烎

1,2,∞

Dr Paul Tennent

and the university of nottingham

turn off the lights, please

A bunch of random, thinned and stateless thoughts around the Web

%d bloggers like this: