The Fast Bilateral Solver

@article{Barron2016TheFB,
  title={The Fast Bilateral Solver},
  author={Jonathan T. Barron and Ben Poole},
  journal={ArXiv},
  year={2016},
  volume={abs/1511.03296}
}
We present the bilateral solver, 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. Our technique is capable of matching or improving upon state-of-the-art results on several different computer vision tasks (stereo, depth superresolution, colorization, and semantic segmentation) while being 10–1000\(\times \) faster than baseline techniques with comparable accuracy, and… 

Real-Time Semantic Segmentation-Based Stereo Reconstruction

TLDR
A novel semantic segmentation-based stereo reconstruction method that can keep up with the accuracy of the state-of-the art approaches while running in real time and introduces several improvements to computation, aggregation, and optimization by adapting existing techniques to integrate additional surface information given by each semantic class.

Deep Bilateral Learning for Stereo Image Super-Resolution

TLDR
This letter uses a parallax-attention module to incorporate information from left and right views to learn content-aware bilateral filters, which are used to recover missing details at different spatial locations while preserving stereo consistency in a bilateral stereo super-resolution network.

Solving Vision Problems via Filtering

TLDR
It is shown that similar solutions can be obtained more easily via filtering, obviating the need to solve a potentially dense system of equations using slow iterative methods.

A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereo

TLDR
A novel solver that iteratively solves for per-view depth map and normal map by optimizing an energy potential based on the locally planar assumption is introduced, which can be trained end-to-end and consistently improves the depth quality over both conventional and deep learning based MVS pipelines.

Image-Guided Depth Upsampling via Hessian and TV Priors

TLDR
A method that combines sparse depth (LiDAR) measurements with an intensity image and to produce a dense high-resolution depth image is proposed and achieves a depth reconstruction performance comparable to or better than other model-based methods.

Learned Collaborative Stereo Refinement

TLDR
The optimization based structure of the refinement module allows us to compute eigen disparity maps, which reveal structural properties of the authors' refinement module, and the efficiency of the method is demonstrated on the publicly available stereo benchmarks Middlebury 2014 and Kitti 2015.

End-to-End learning of cost-volume aggregation for real-time dense stereo

TLDR
This paper presents a new deep learning-based approach for dense stereo matching that uses a deep convolutional network to predict the local parameters of cost volume aggregation process, which is implemented using differentiable domain transform.

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.

NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

TLDR
NICE-SLAM is presented, a dense SLAM system that incorporates multi-level local information by introducing a hierarchical scene representation and optimizing this representation with pre-trained geometric priors enables detailed reconstruction on large indoor scenes.
...

References

SHOWING 1-10 OF 56 REFERENCES

100+ Times Faster Weighted Median Filter (WMF)

  • Qi ZhangLi XuJiaya Jia
  • Computer Science
    2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
TLDR
A new joint-histogram representation, median tracking, and a new data structure that enables fast data access are proposed that reduce computation complexity from O(r2) to O( r) where r is the kernel size.

Joint bilateral upsampling

TLDR
It is demonstrated that in cases, such as those above, the available high resolution input image may be leveraged as a prior in the context of a joint bilateral upsampling procedure to produce a better high resolution solution.

Computing the stereo matching cost with a convolutional neural network

  • Jure ZbontarYann LeCun
  • Computer Science
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
TLDR
This work trains a convolutional neural network to predict how well two image patches match and uses it to compute the stereo matching cost, which achieves an error rate of 2.61% on the KITTI stereo dataset.

Fast surface interpolation using hierarchical basis functions

  • R. Szeliski
  • Computer Science
    Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1989
TLDR
In the present paper, an alternative to multigrid relaxation which is much easier to implement is presented, which uses conjugate-gradient descent in conjunction with a hierarchical (multiresolution) set of basis functions.

Real-time edge-aware image processing with the bilateral grid

TLDR
A new data structure---the bilateral grid, that enables fast edge-aware image processing that parallelize the algorithms on modern GPUs to achieve real-time frame rates on high-definition video.

Fast Guided Filter

TLDR
The guided filter can be simply sped up from O(N) time to O( N/s^2) time for a subsampling ratio s, leading to a speedup of >10x with almost no visible degradation.

Fast bilateral-space stereo for synthetic defocus

TLDR
This paper presents a technique for efficiently producing disparity maps using a novel optimization framework in which inference is performed in “bilateral-space”, and produces higher-quality “defocus” results than other stereo algorithms while also being 10 - 100× faster than comparable techniques.

Sparse depth super resolution

  • Jiajun LuD. Forsyth
  • Computer Science, Geology
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
TLDR
A method to produce detailed high resolution depth maps from aggressively subsampled depth measurements using an image combined with a low resolution depth map that outperforms recent state of the art methods quantitatively and qualitatively.

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.

Combinatorial preconditioners and multilevel solvers for problems in computer vision and image processing

...