Difference between revisions of "Surface normal estimation by Spiral Codes"

From ISLAB/CAISR
 
Line 2: Line 2:
 
|Summary=Estimating 3d surface normal from a single image
 
|Summary=Estimating 3d surface normal from a single image
 
|References=J. Bigun "Vision with Direction", chapter 11, Springer, 2016.
 
|References=J. Bigun "Vision with Direction", chapter 11, Springer, 2016.
|Prerequisites=Image Analysis
+
|Prerequisites=Image Analysis, multi-variable calculus
 
|Supervisor=Josef Bigun
 
|Supervisor=Josef Bigun
 
|Level=Master
 
|Level=Master
 
|Status=Open
 
|Status=Open
 
}}
 
}}
Estimating 3d surface normal from a single image by using orientation statistics of a priori known patterns.
+
Estimating 3d surface normal from a single image is an ill defined problem.
 +
However, if there is knowledge about the viewed pattern of a surface, the surface normal
 +
can be estimated from (2d) local image orientation statistics.
 +
 
 +
The project will have the goal to review methods extracting surface orientation in 3d from 2D texture: shape from texture. Additionally, the question will be studied for a restricted class of patterns, in the form of spiral patterns.
 +
 
 +
Good knowledge in calculus and image analysis is required.

Latest revision as of 12:30, 11 October 2021

Title Surface normal estimation by Spiral Codes
Summary Estimating 3d surface normal from a single image
Keywords
TimeFrame
References J. Bigun "Vision with Direction", chapter 11, Springer, 2016.
Prerequisites Image Analysis, multi-variable calculus
Author
Supervisor Josef Bigun
Level Master
Status Open


Estimating 3d surface normal from a single image is an ill defined problem. However, if there is knowledge about the viewed pattern of a surface, the surface normal can be estimated from (2d) local image orientation statistics.

The project will have the goal to review methods extracting surface orientation in 3d from 2D texture: shape from texture. Additionally, the question will be studied for a restricted class of patterns, in the form of spiral patterns.

Good knowledge in calculus and image analysis is required.