Deformable Image Registration - ULisboa

Deformable Image Registration

Adrien Bartoli

ALCoV – ISIT

Université d’Auvergne

Clermont-Ferrand, France

Fourth Tutorial on Computer Vision in a Nonrigid World ICCV’11, Barcelona, Spain – octobre 6, 2011

Lourdes Agapito, Adrien Bartoli, Alessio Del Bue

The Equations of Registration


The warp 𝜑𝑖: Ω → ℝ2 is a function that transfers pixels between images

Warp visualization grid

→ To relate the content of at least two images

𝜑1 𝜑2

𝜑3 ROI Ω ∈ ℕ2

Difficulty: Variation of the Imaged Appearance

External occlusions, color Self-occlusion Field of view + lighting

Scene geometry Surface appearance Imaging conditions

• External occlusions • Self-occlusions • Wrinkles and foldings • Temporal continuity • Extensibility • Etc.

• Lighting • Lack of / repeating texture • Reflectance • Specularities • Transparency • Etc.

• Pose • Field of view • Affine vs perspective • Optical and motion blur • Auto-exposure, saturation • Etc.

Template

Semantic Matching

The Warp Function 𝜑

The warp 𝜑:Ω → ℝ2 is continuous and piecewise ‘smooth’

3D deformation Ψ ∈ 𝐶0

Warp 𝜑 ∈ 𝐶0

Image Pair Versus Video Registration

𝜑1

𝜑2 𝜑3

Video registration

Image pair registration

𝜑

min𝜑∈𝐶0ℰ[𝜑]

A variational optimization problem

ℰ is the cost functional

Computational Warp Representation

A warp 𝜑 is an interpolant between pairs of fixed/moving driving features

source target

fixed

moving

Computational Warp Representation

Encompasses the Flow-Field, Mesh Interpolation, Radial Basis Functions (and so the Thin-Plate Spline), Tensors Product (and so the Cubic B-Spline Free-Form Deformation), etc.

[Brunet et al., IJCV’11 ; Bartoli et al., IJCV’10]

The Cost Functional

Data term • Relates the warp to the image content • Bayesian likelihood

Regularization term • Measures closeness to prior knowledge • Bayesian prior

Regularization weight • Hyperparameter • Trades-off data-regularization • ≈ Bayesian noise variance

Overfitting About fine Underfitting Underfitting

Measuring Unsmoothness

This energy is Linear Least Squares (and so convex) for Linear Basis Expansion warps

Partial derivatives of order 1 and 2 are commonly used:

[Bookstein, PAMI’89]

Measuring Data Fitting

1 – Feature-based registration

• Wide-baseline

• Keeps only geometric features

• Less accurate than pixel-based

• Small-baseline

• Uses the whole image content

• More accurate than feature-based

2 –Pixel-based registration

Warp Estimation from Keypoint Matches

Property: for Linear Basis Expansion warps the above cost function is Linear Least Squares

Keypoint Detection

• Locations where the image changes significantly – Repeatable (stable over appearance variation)

– Accurately localised

– Discriminable

• Literature is massive (Harris, SIFT, SURF, etc.)

Basic Keypoint-Based Workflow

Keypoint detection Warp estimation Putative keypoint matching

Putative Keypoint Matching

There are always mismatches

Robust Keypoint-Based Workflow

Warp estimation Putative keypoint matching Robust keypoint matching

Robust Estimation

Local consistency → strong evidence of correctness 1 – Keep all locally consistent matches as strong correct matches 2 – Add matches locally consistent with strong correct matches

[Pizarro et al, IJCV, to appear]

• Global methods (RANSAC, M-estimators, etc.) are not adapted • Local methods do much better

Robust Estimation Results

Robust Estimation Results

Inaccuracies are (partly) due to self-occlusions

Self-Occlusions

Current warp profile

Desired warp profile

Self-occlusion boundary

Self-occlusions

Self-occlusion

Visible

Self-Occlusions

Differential properties:

Let 𝜂:ℝ2 → ℝ give the warp’s Jacobian (𝜂 =𝜕𝜑

𝜕𝐪)

𝜂 𝐪 ≤ 0 means point q is self-occluded

𝜂 𝐪 > 0 is not conclusive

Current warp profile

Self-occlusions

Differential properties

Desired warp profile

𝜂 = 0

𝜂 ≥ 0

The ‘Oversmoothing’ Algorithm

[Pizarro et al, IJCV, to appear]

1

2

3

Self-Occlusion Estimation Results

Initial warp Partial self-occlusion map Self-occlusion resistant warp

1 2 3

Measuring Data Fitting

1 – Feature-based registration

• Wide-baseline

• Keeps only geometric features

• Less accurate than pixel-based

• Small-baseline

• Uses the whole image content

• More accurate than feature-based

2 –Pixel-based registration

Warp Estimation from the Brightness Constancy Assumption

Warp Estimation from the Brightness Constancy Assumption

The above cost function is Nonlinear Least Squares → Iterative local minimization (gradient descent-like)

Color Change

Explicit Photometric Transformation

Video: no photometric model Video: affine photometric model

Template Image

[Bartoli, PAMI’08]

Light-Invariant Registration

Video: no photometric model

Light-invariant registration

Template Image

[Pizarro et al, SCIA’07, CVPR’08]

Registration Results

Video: visualization grid, retexturing Video: retexturing

Videos: original, visualization grid and retexturing

Videos: original, retargetting and retexturing

What About External Occlusions?

Video: failure in case of external occlusion

Robustification

Idea: inhibitate the data terms that get `too large'

The square loss function is replaced by an M-estimator ½

Robust Registration Results

Videos: visualization grid and template with outlying pixels in blue

What About Self-Occlusions?

Video: failure in case of self-occlusion

The ‘Shrinker’ Approach: Principle

[Gay-Bellile et al., PAMI’10]

Warp profile

The ‘Shrinker’ Approach: Implementation

Self-Occlusion Detection Results

Videos (with self-occlusion): visualization grid and template with self-occluded pixels in white


Videos (with external and self-occlusion): visualization grid and template with self-occluded pixels in white and external occluded pixels in blue


Videos (with self-occlusion): visualization grid and template with self-occluded pixels in white


Video (with self-occlusion): retexturing

+

ISMAR logo

Video (with self-occlusion): retexturing

Registration Workflow for an Image Pair

1. Feature-based initialization

– Convex optimizations (Linear Least Squares)

– Wide baseline, less accurate

– Partial detection of self-occlusions

2. Pixel-based refinement

– Non-convex optimization

– Short baseline, more accurate

– Complete detection of self-occlusions

Registering a Video

𝜑1 𝜑2

𝜑3

The warps 𝜑1, … , 𝜑𝑛 are temporally coherent

min𝜑1,…,𝜑𝑛 ℰ𝑑[𝜑1, … , 𝜑𝑛] + 𝜆𝑠ℰ𝑠[𝜑1, … , 𝜑𝑛] +𝜆𝑡ℰ𝑡[𝜑1, … , 𝜑𝑛]

data Spatial smoothness

Temporal smoothness

Data (L1 norm)

Spatial smoothness

Temporal smoothness

Subspace Trajectory Constraints

[Garg et al, EMMCVPR’11]

𝜑𝑖 ≈ 𝑢𝑖 Frame 1

Frame 𝑖 Frame 𝑛 Fixed 2D trajectory basis

Coefficients

• PCA of sparse tracks • Low frequency

components of DCT • B-Splines

𝑢𝑖 𝐪 = B𝑖𝛼(𝐪)

min𝜑1,…,𝜑𝑛𝛼 𝐪 , 𝐪∈Ω

ℰ𝑑[𝜑𝑖]

𝑛

𝑖=1

+ 𝜆𝑡 𝑢𝑖 − 𝜑𝑖 2

𝑛

𝑖=1

+ 𝜆𝑠𝜕𝛼

𝜕𝐪1

Ω

𝐪

Subspace Trajectory Constraints

[Garg et al, EMMCVPR’11]

For 𝑖 = 1,… , 𝑛

min𝜑𝑖ℰ𝑑 𝜑𝑖 + 𝜆𝑡 𝑢𝑖 − 𝜑𝑖 2

Initialize all warps to identity

min𝛼 𝐪 , 𝐪∈Ω

𝜆𝑡 𝑢𝑖 − 𝜑𝑖 2

𝑛

𝑖=1

+ 𝜆𝑠𝜕𝛼

𝜕𝐪1

Solved point-wise

Can be solved independently for each basis

loop

1 2

1

2

This is embedded in a coarse-to-fine approach

Data (L1 norm)

Spatial smoothness

Temporal smoothness

min𝜑1,…,𝜑𝑛𝛼 𝐪 , 𝐪∈Ω

ℰ𝑑[𝜑𝑖]

𝑛

𝑖=1

+ 𝜆𝑡 𝑢𝑖 − 𝜑𝑖 2

𝑛

𝑖=1

+ 𝜆𝑠𝜕𝛼

𝜕𝐪1

→ Show « vid_flag_orig.mp4 »

Video Registration Results

Video: registration error of video registration

From left to right • Subspace trajectory constraints, PCA basis [Garg et al, EMMCVPR’11] • Subspace trajectory constraints, DCT basis [Garg et al, EMMCVPR’11] • Large Displacement Optical Flow [Brox et al, ECCV’10] • Baseline method (no motion basis) [Wedel et al, 2009] • Pairwise B-Spline pixel-based estimation [Pizarro et al, IJCV]


Adrien Bartoli

ALCoV – ISIT

Université d’Auvergne

Clermont-Ferrand, France

Fourth Tutorial on Computer Vision in a Nonrigid World ICCV’11, Barcelona, Spain – octobre 6, 2011

Lourdes Agapito, Adrien Bartoli, Alessio Del Bue

Deformable Image Registration - ULisboa

Documents