Accelerating Spatially Varying Gaussian Filters Jongmin Baek and David E. Jacobs Stanford University
Motivation Input Gaussian Filter Spatially Varying Gaussian Filter
1) Accelerating Spatially Varying Gaussian Filters 2) Accelerating Spatially Varying Gaussian Filters 3) Accelerating Spatially Varying Gaussian Filters 4) Applications Roadmap
Gaussian Filters Position Value
Gaussian Filters Each output value …
Gaussian Filters … is a weighted sum of input values …
Gaussian Filters … whose weight is a Gaussian …
Gaussian Filters … in the space of the associated positions.
Gaussian Blur Gaussian Filters: Uses
Bilateral Filter Gaussian Filters: Uses
Non-local Means Filter Gaussian Filters: Uses
Applications Denoising images and meshes Data fusion and upsampling Abstraction / Stylization Tone-mapping ... Gaussian Filters: Summary Previous work on fast Gaussian Filters Bilateral Grid (Chen, Paris, Durand; 2007) Gaussian KD-Tree (Adams et al.; 2009) Permutohedral Lattice (Adams, Baek, Davis; 2010)
Summary of Previous Implementations: A separable blur flanked by resampling operations. Exploit the separability of the Gaussian kernel. Gaussian Filters: Implementations
Spatially Varying Gaussian Filters Spatially varying covariance matrix Spatially Invariant
Trilateral Filter (Choudhury and Tumblin, 2003) Tilt the kernel of a bilateral filter along the image gradient. “Piecewise linear” instead of “Piecewise constant” model. Spatial Variance in Previous Work
Spatially Varying Gaussian Filters: Tradeoff Benefits: Can adapt the kernel spatially. Better filtering performance. Cost: No longer separable. No existing acceleration schemes. Input Bilateral-filtered Trilateral-filtered
Problem: Spatially varying (thus non-separable) Gaussian filter Existing Tool: Fast algorithms for spatially invariant Gaussian filters Solution: Re-formulate the problem to fit the tool. Need to obey the “piecewise-constant” assumption Acceleration
Naïve Approach (Toy Example) I LOST THE GAME Input Signal Desired Kernel filtered w/ 1 filtered w/ 2 filtered w/ 3 filtered w/ Output Signal 4
In practice, the # of kernels can be very large. Challenge #1 Pixel Location x Desired Kernel K(x) Range of Kernels needed
Sample a few kernels and interpolate. Solution #1 Desired Kernel K(x) Sampled kernels Interpolate result! Pixel Location x K1K1 K2K2 K3K3
Interpolation needs an extra assumption to work: The covariance matrix Ʃ i is either piecewise- constant, or smoothly varying. Kernel is spatially varying, but locally spatially invariant. Assumptions
Runtime scales with the # of sampled kernels. Challenge #2 Desired Kernel K(x) Filter only some regions of the image with each kernel. (“support”) Pixel Location x Sampled kernels K1K1 K2K2 K3K3
In this example, x needs to be in the support of K 1 & K 2. Defining the Support Desired Kernel K(x) Pixel Location x K1K1 K2K2 K3K3
Dilating the Support Desired Kernel K(x) Pixel Location x K1K1 K2K2 K3K3
Algorithm 1) Identify kernels to sample. 2) For each kernel, compute the support needed. 3) Dilate each support. 4) Filter each dilated support with its kernel. 5) Interpolate from the filtered results.
Algorithm 1) Identify kernels to sample. 2) For each kernel, compute the support needed. 3) Dilate each support. 4) Filter each dilated support with its kernel. 5) Interpolate from the filtered results. K1K1 K2K2 K3K3
Algorithm 1) Identify kernels to sample. 2) For each kernel, compute the support needed. 3) Dilate each support. 4) Filter each dilated support with its kernel. 5) Interpolate from the filtered results. K1K1 K2K2 K3K3
Algorithm 1) Identify kernels to sample. 2) For each kernel, compute the support needed. 3) Dilate each support. 4) Filter each dilated support with its kernel. 5) Interpolate from the filtered results. K1K1 K2K2 K3K3
Algorithm 1) Identify kernels to sample. 2) For each kernel, compute the support needed. 3) Dilate each support. 4) Filter each dilated support with its kernel. 5) Interpolate from the filtered results. K1K1 K2K2 K3K3
Algorithm 1) Identify kernels to sample. 2) For each kernel, compute the support needed. 3) Dilate each support. 4) Filter each dilated support with its kernel. 5) Interpolate from the filtered results. K1K1 K2K2 K3K3
Applications HDR Tone-mapping Joint Range Data Upsampling
Application #1: HDR Tone-mapping Input HDR Detail Base Filter Output Attenuate
Tone-mapping Example Bilateral Filter Kernel Sampling
Application #2: Joint Range Data Upsampling Range Finder Data Sparse Unstructured Noisy Scene Image Output Filter
Synthetic Example Scene Image Ground Truth Depth
Synthetic Example Scene ImageSimulated Sensor Data
Synthetic Example : Result Kernel Sampling Bilateral Filter
Synthetic Example : Relative Error Bilateral Filter Kernel Sampling 2.41% Mean Relative Error0.95% Mean Relative Error
Real-World Example Scene Image Range Finder Data *Dataset courtesy of Jennifer Dolson, Stanford University
Real-World Example: Result Input Bilateral Naive Kernel Sampling
Performance Kernel Sampling Choudhury and Tumblin (2003) Naïve Tonemap s41.54 s s Tonemap s88.08 s s Kernel Sampling (No segmentation) Depth s57.90 s Depth s s
1.A generalization of Gaussian filters Spatially varying kernels Lose the piecewise-constant assumption. 2.Acceleration via Kernel Sampling Filter only necessary pixels (and their support) and interpolate. 3.Applications Conclusion