Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. Computer Science and Artificial Intelligence Lab (CSAIL)
  3. Artificial Intelligence Lab Publications
  4. AI Memos (1959 - 2004)
  5. Learning Object-Independent Modes of Variation with Feature Flow Fields

Learning Object-Independent Modes of Variation with Feature Flow Fields

Thumbnail Image
Download
Name

AIM-2001-021.pdf

Size

795.54 KB

Format

Adobe PDF

Checksum (MD5)

745bab553a4ce83f91d0b59320e5998c

Thumbnail Image
Download
Name

AIM-2001-021.ps

Size

7.85 MB

Format

PostScript

Checksum (MD5)

ced05c8a3f33acc1cbfd13955e3cdcdf

Author(s)
Miller, Erik G.
•
Tieu, Kinh
•
Stauffer, Chris P.
Date Issued
September 1, 2001
Series/Report no.
AIM-2001-021
Abstract
We present a unifying framework in which "object-independent" modes of variation are learned from continuous-time data such as video sequences. These modes of variation can be used as "generators" to produce a manifold of images of a new object from a single example of that object. We develop the framework in the context of a well-known example: analyzing the modes of spatial deformations of a scene under camera movement. Our method learns a close approximation to the standard affine deformations that are expected from the geometry of the situation, and does so in a completely unsupervised (i.e. ignorant of the geometry of the situation) fashion. We stress that it is learning a "parameterization", not just the parameter values, of the data. We then demonstrate how we have used the same framework to derive a novel data-driven model of joint color change in images due to common lighting variations. The model is superior to previous models of color change in describing non-linear color changes due to lighting.
Subjects
AI
Invariance
Optical Flow
Color Constancy
Object Recognition
image manifold
Persistent DSpace Link
http://hdl.handle.net/1721.1/6659
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.