Mean-Field Theory and Its Applications In Computer Vision3 1
Gaussian Pairwise Potential 2 Spatial Expensive message passing can be performed by cross-bilateral filtering Range
Cross bilateral filter 3 outputinput reproduced from [Durand 02] outputinput
Efficient Cross-Bilateral Filtering Based on permutohedral lattice (PLBF) 2 Embed the points on the permutohedral lattice Apply Gaussian Blurring 4
Efficient Cross-Bilateral Filtering Based on permutohedral lattice (PLBF) 2 Embed the points on the permutohedral lattice Apply Gaussian Blurring 5 Based on the domain-transform (DTBF) 3 Project the point to lower dimension Perform filtering in the transformed domain
Efficient Cross-Bilateral Filtering Based on permutohedral lattice (PLBF) 2 Embed the points on the permutohedral lattice Apply Gaussian Blurring 6 Based on the domain-transform (DTBF) 3 Project the point to lower dimension Perform filtering in the transformed domain Filtering in frequency domain Apply fast fourier transform convolution in (s) domain=multiplication in (f) domain
Barycentric Interpolation 7
Efficient Cross-Bilateral Filtering 8
Permutohedral Lattice based filtering For each pixel (x, y) 9 Downsample all the points (dependent on standard deviations)
Embed to the permutohedral lattice Embed each downsampled points to the lattice 10
Embed to the permutohedral lattice Embed each downsampled points to the lattice 11
Embed to the permutohedral lattice Embed each downsampled points to the lattice 12
Embed to the permutohedral lattice Embed each downsampled points to the lattice 13
Gaussian blurring Apply Gaussian blurring along axes 14
Gaussian blurring Apply Gaussian blurring along axes 15
Gaussian blurring Apply Gaussian blurring along axes 16
Splatting Upsample the points 17
Splatting Upsample the points 18
PLBF Final upsampled points 19
Domain Transform Filtering 20 Project points in low-dimension preserving the distance in the high dimension Projecting to the original space Filtering performed in low-dimension space
Distance in high-dimension space 21
Filtering in high-dimension space 22 Spatial Range Inefficient
Projection in low-dimension space 23 Project to low-dimension Maintain geodesic distance high-dimension space
Projection in low-dimension space 24 Project to low-dimension Maintain geodesic distance high-dimension space
Projection in low-dimension space 25 Project to low-dimension Maintain geodesic distance high-dimension space
Gaussian blurring in low-dimension 26 Apply Gaussian blurring in low-dimension space
Project 27 Project the blurred values in the original space
Project 28 Project the blurred values in the original space
PLBF Vs DTBF 29 Filter parameter: PLBF runtime is inversely proportional to the kernel size defined over space and range Use PLBF with the relatively large (~10) range Use DTBF with relatively smaller (~1-2) range Processing Time: Both linear in the number of pixels
Filtering in frequency domain 30
Convergence 31 Iteration vs. KL-divergence value In theory: (since parallel update) convergence is not guaranteed In practice: converges observe a convergence
MSRC-21 dataset colour images, 320x213 size, 21 object classes
MSRC-21 dataset colour images, 320x213 size, 21 object classes RuntimeStandard ground truthAccurate ground truth GlobalAverageGlobalAverage Unary Classifiers ± ±2.3 Grid CRF1 sec ± ±1.8 Robust Pn30 sec ± ±1.5 Dense CRF0.2 sec ± ±0.7
PascalVOC-10 dataset colour images, 320x213 size, 21 object classes
PascalVOC-10 dataset colour images, 320x213 size, 21 object classes RuntimeOverallAv. RecallAv. I/U Dense CRF0.67 sec
Long-range connections 36 Accuracy o n increasing the spatial and range standard deviations On MSRC-21 spatial – 61 pixels, range – 11
Long-range connections 37 On increasing the spatial and range standard deviations On MSRC-21 spatial – 61 pixels, range – 11
Long-range connections 38 Sometimes propagates misleading information
Mean-field Vs. Graph-cuts 39 Measure I/U score on PascalVOC-10 segmentation Increase standard deviation for mean-field Increase window size for graph-cuts method Both achieve almost similar accuracy
Mean-field Vs. Graph-cuts 40 Measure I/U score on PascalVOC-10 segmentation Increase standard deviation for mean-field Increase window size for graph-cuts method Time complexity very high, making infeasible to work with large neighbourhood system