Download presentation
Presentation is loading. Please wait.
Published byEdgar Walker Modified over 9 years ago
1
Verifying the “Consistency” of Shading Patterns and 3-D Structures Pawan Sinha & Edward Adelson
2
What is the 3D Structure of Each Image?
3
Infinite Number of Possible Interpretations
4
Goal 1: 3D Shape Recovery
5
Goal 2: Check Shading Consistency
6
Input Patterns
7
Goal 1: Propose 3D Structure ● Questions: – What distinguishes correct structure? – How to search for it algorithmically?
8
What Distinguishes Correct Structure? WrongRight
9
What Distinguishes Correct Structure? ● Low “Complexity” – Low Angle Variance – Planarity of Faces – Overall Compactness
10
How to Search? ● Minimize Cost Function – How to weight constraints? – Cumbersome ● Incremental Solution – Start with 2-D Line Drawing – “Pull” vertices until regularity is maximized ● i.e. Gradient descent in regularity space
11
Incremental Solution
12
Goal 2: Check Shading Consistency ● Given – 3D structure – 2D gray-level image ● Assume – Structure is uniformly colored ● Find – Single light source to account for shading
13
Quantitative Approach ● Given: – Lambertian Reflectance Model – Surface Normal – Surface Brightness ● Defines: – A cone of valid light directions for each surface
14
Cone of valid light direction N=surface normal E=brightness N
15
Quantitative Approach ● Consider cones for all surfaces ● Intersection is direction of illumination
16
Problems ● Small changes in grey lead to no solution Surface l 3 changes brightness Gradient Space Input Patterns Before After Intersection
17
Qualitative Approach ● Observation – Human vision ● Good at judging relation between brightness ● Bad at judging absolute brightness ● So... – Use binary relations to: ● find light source ● Not commit to particular reflectance function
18
Qualitative Approach ● Each surface now defines a hemisphere of possible light directions – Overall consistency implies finding a non-null intersection of hemispheres
19
Qualitative Approach ● Hemisphere ~ set of vectors t s.t Angle between s and t is less than 90
20
Qualitative Approach ● Hemisphere ~ set of vectors t s.t sij is defined between a surface i and surface j, with normals ni and nj
21
Qualitative Approach ● Hemisphere ~ set of vectors t s.t s is perpindicular to the average of the normals
22
Qualitative Approach ● Hemisphere ~ set of vectors t s.t s is perpindicular to plane defined by the normals
23
Qualitative Approach ● Hemisphere ~ set of vectors t s.t The angle between s and ni is less than 90 & the angle between s and nj is greater
24
Solution ● Solution to constraints lie on a convex polygon on the unit sphere. Direction of agreement
25
Is it consistent? ● If no polygons found that satisfy all constraints, then – Shading is not consistent No maximum
26
Largely Solveable ● For each polygon, count # of constraints matched – A maximum indicates most likely lighting direction
27
Compound Edges ● What do unsatisfied constraints represent? – Compound edge – where surface changes color, not just shading Compound edges
28
Justification ● Why do shape derivation with line drawings and not brightness? – Humans can use edges ● Can humans use grey level? – It seems like it – An experiment
29
An Experiment ● Random Height Tesselation – Can human determine 3d structure? 3D Representation Overhead View
30
Limitations ● Polyhedral objects only ● Later research addresses contoured objects w/ smoothly changing brightness.
31
Conclusions ● Humans mostly use edges to determine 3D structure ● Use shading to verify this determination ● Algorithm effective for polyhedra
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.