The Domain Transform Solver

@article{Bapat2019TheDT,
  title={The Domain Transform Solver},
  author={A. Bapat and Jan-Michael Frahm},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={6007-6016}
}
  • A. Bapat, Jan-Michael Frahm
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We present a novel framework for edge-aware optimization that is an order of magnitude faster than the state of the art while maintaining comparable results. Our key insight is that the optimization can be formulated by leveraging properties of the domain transform, a method for edge-aware filtering that defines a distance-preserving 1D mapping of the input space. This enables our method to improve performance for a wide variety of problems including stereo, depth super-resolution, render from… Expand
Probabilistic Pixel-Adaptive Refinement Networks
Encoder-decoder networks have found widespread use in various dense prediction tasks. However, the strong reduction of spatial resolution in the encoder leads to a loss of location information asExpand
Fast Optical Flow Extraction From Compressed Video
TLDR
The fast optical flow extractor is a filtering method that recovers artifact-free optical flow fields from HEVC-compressed video, and achieves a 100-fold speed-up in the running times compared to similar methods, while producing subpixel-accurate flow estimates. Expand
Fast Optical Flow Extraction from Compressed Video
TLDR
The fast optical flow extractor is a filtering scheme that recovers artifact-free optical flow fields from HEVC-compressed video and achieves a 10-fold speed-up in the running times compared to similar methods. Expand
Deterministic Guided LiDAR Depth Map Completion
TLDR
A non-deep learning-based approach to densify a sparse LiDAR-based depth map using a guidance RGB image and the pinhole camera model is used for the interpolation process, which shows that it outperforms the state-of-the-art non- Deep Learning-based methods, in addition to several deep learning- based methods. Expand

References

SHOWING 1-10 OF 51 REFERENCES
The Fast Bilateral Solver
TLDR
A novel algorithm for edge-aware smoothing that combines the flexibility and speed of simple filtering approaches with the accuracy of domain-specific optimization algorithms, fast, robust, straightforward to generalize to new domains, and simple to integrate into deep learning pipelines. Expand
Superpixel meshes for fast edge-preserving surface reconstruction
TLDR
This work proposes a novel surface reconstruction method based on image edges, superpixels and second-order smoothness constraints, producing meshes comparable to classic MVS surfaces in quality but orders of magnitudes faster. Expand
Bilateral guided upsampling
TLDR
An algorithm to accelerate a large class of image processing operators by fitting local curves that map the input to the output that faithfully models state-of-the-art operators for tone mapping, style transfer, and recoloring is presented. Expand
Domain transform for edge-aware image and video processing
TLDR
The use of 1D operations leads to considerable speedups over existing techniques and potential memory savings; its computational cost is not affected by the choice of the filter parameters; and it is the first edge-preserving filter to work on color images at arbitrary scales in real time, without resorting to subsampling or quantization. Expand
Image Guided Depth Upsampling Using Anisotropic Total Generalized Variation
TLDR
This work formulate a convex optimization problem using higher order regularization for depth image up sampling, and derives a numerical algorithm based on a primal-dual formulation that is efficiently parallelized and runs at multiple frames per second. Expand
Multiscale shape and detail enhancement from multi-light image collections
TLDR
A new image-based technique for enhancing the shape and surface details of an object by computing a multiscale decomposition based on the bilateral filter and reconstructing an enhanced image that combines detail information at each scale across all the input images. Expand
Edge-preserving decompositions for multi-scale tone and detail manipulation
TLDR
This paper advocates the use of an alternative edge-preserving smoothing operator, based on the weighted least squares optimization framework, which is particularly well suited for progressive coarsening of images and for multi-scale detail extraction. Expand
Patch Match Filter: Efficient Edge-Aware Filtering Meets Randomized Search for Fast Correspondence Field Estimation
TLDR
This paper presents a generic and fast computational framework for general multi-labeling problems called Patch Match Filter (PMF), and explores effective and efficient strategies to weave together these two fundamental techniques developed in isolation, i.e., Based-based randomized search and efficient edge-aware image filtering. Expand
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
TLDR
A new superpixel algorithm is introduced, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels and is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation. Expand
Colorization using optimization
TLDR
This paper presents a simple colorization method that requires neither precise image segmentation, nor accurate region tracking, and demonstrates that high quality colorizations of stills and movie clips may be obtained from a relatively modest amount of user input. Expand
...
1
2
3
4
5
...