Fast cost-volume filtering for visual correspondence and beyond

@article{Rhemann2011FastCF,
  title={Fast cost-volume filtering for visual correspondence and beyond},
  author={Christoph Rhemann and Asmaa Hosni and Michael Bleyer and Carsten Rother and Margrit Gelautz},
  journal={CVPR 2011},
  year={2011},
  pages={3017-3024}
}
Many computer vision tasks can be formulated as labeling problems. The desired solution is often a spatially smooth labeling where label transitions are aligned with color edges of the input image. We show that such solutions can be efficiently achieved by smoothing the label costs with a very fast edge preserving filter. In this paper we propose a generic and simple framework comprising three steps: (i) constructing a cost volume (ii) fast cost volume filtering and (iii) winner-take-all label… Expand
Fast Cost-Volume Filtering for Visual Correspondence and Beyond
TLDR
This work proposes a generic and simple framework comprising three steps: constructing a cost volume, fast cost volume filtering, and 3) Winner-Takes-All label selection that achieves 1) disparity maps in real time whose quality exceeds those of all other fast (local) approaches on the Middlebury stereo benchmark, and 2) optical flow fields which contain very fine structures as well as large displacements. Expand
Volumetric Correspondence Networks for Stereo Matching and Optical Flow
Many classic tasks in vision, such as the estimation of optical flow or stereo disparities, can be cast as dense correspondence matching. Well-known techniques for doing so make use of a cost volume,Expand
Low Compute and Fully Parallel Computer Vision with HashMatch
TLDR
This paper presents a new general framework for a variety of computer vision labeling tasks, called HashMatch, designed to be both fully parallel, i.e. each pixel is independently processed, and low-compute, with a model complexity an order of magnitude less than existing CNN and CRF-based approaches. Expand
PatchMatch Filter: Edge-Aware Filtering Meets Randomized Search for Visual Correspondence
TLDR
A generic and fast computational framework for general multi-labeling problems called PatchMatch Filter (PMF) is presented and a simple yet effective cross-scale consistency constraint is proposed, which handles labeling estimation for large low-textured regions more reliably than a single-scale PMF algorithm. Expand
Accelerating Cost Volume Filtering Using Salient Subvolumes and Robust Occlusion Handling
TLDR
This paper proposes the Accelerated Cost Volume Filtering (ACF) method which identifies salient subvolumes in the cost volume and develops an Occlusion Handling (OH) technique, which uses superpixels and performs label propagation via a simulated annealing inspired method. 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
Cost volume refinement filter for post filtering of visual corresponding
TLDR
Experimental results show that the generalized formulation of cost volume refinement filtering outperform the conventional approaches, and also show what the format of CVRF is appropriate for various applications of stereo matching and optical flow estimation. Expand
Efficient Coarse-to-Fine Patch Match for Large Displacement Optical Flow
TLDR
This paper proposes a propagation step with constrained random search radius between adjacent levels on the hierarchical architecture that outperforms the state of the art on MPI-Sintel and KITTI, and runs much faster than the competing methods. Expand
Four-direction global matching with cost volume update for stereovision.
  • Yusheng Jin, Hong Zhao, Penghui Bu
  • Medicine
  • Applied optics
  • 2021
TLDR
This paper proposes a novel, to the best of the knowledge, four-direction global matching with a cost volume update scheme to cope with textureless regions and occlusion and demonstrates that the method outperforms typical SGM-based cost aggregation approaches and other state-of-the-art local methods. Expand
Combining Features and Semantics for Low-level Computer Vision
TLDR
This thesis proposes an efficient way of training a context network with a large receptive field size on top of a local network using dilated convolutions on patches and presents a method for learning context-aware features for solving optical flow using discrete optimization. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 53 REFERENCES
Fast Cost-Volume Filtering for Visual Correspondence and Beyond
TLDR
This work proposes a generic and simple framework comprising three steps: constructing a cost volume, fast cost volume filtering, and 3) Winner-Takes-All label selection that achieves 1) disparity maps in real time whose quality exceeds those of all other fast (local) approaches on the Middlebury stereo benchmark, and 2) optical flow fields which contain very fine structures as well as large displacements. Expand
Temporally Consistent Disparity and Optical Flow via Efficient Spatio-temporal Filtering
TLDR
This paper presents a new efficient algorithm for computing temporally consistent disparity maps from video footage that considerably improves over frame-by-frame methods for both stereo and optical flow; and outperforms the state-of-the-art for local space-time stereo approaches. Expand
Cross-Based Local Stereo Matching Using Orthogonal Integral Images
TLDR
An area-based local stereo matching algorithm for accurate disparity estimation across all image regions, and is among the best performing local stereo methods according to the benchmark Middlebury stereo evaluation. Expand
LogCut - Efficient Graph Cut Optimization for Markov Random Fields
TLDR
This paper proposes a new approach to the optimization of multi-labeled MRFs based on iterative application of binary graph cut, and demonstrates that for applications such as optical flow, image restoration, and high resolution stereo, this gives an order of magnitude speed-up. Expand
Constant Time Stereo Matching
  • Myung-Ho Ju, Hang-Bong Kang
  • Mathematics, Computer Science
  • 2009 13th International Machine Vision and Image Processing Conference
  • 2009
TLDR
The proposed stereo matching method that use domain weight and range weight similar to those in the bilateral filter shows constant time O(1) for the stereo matching and the accuracy of generated depth map is as good as the ones suggested by recent methods. Expand
Near Real-Time Stereo With Adaptive Support Weight Approaches
Algorithms based on the adaptive support weight strategy currently represent the state-of-the-art in local ster eo matching. Unfortunately, their good-quality results come at the price of highExpand
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
TLDR
This paper has designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can easily be extended to include new algorithms. Expand
Local stereo matching using geodesic support weights
TLDR
The proposed algorithm is the top performer among local stereo methods at the current state-of-the-art in local stereo matching by using the geodesic distance transform. Expand
Geodesic image and video editing
TLDR
The introduction of a Generalized Geodesic Distance Transform (GGDT), based on soft masks, provides a unified framework to address several edge-aware editing operations, and generalizes naturally to n-dimensional data. Expand
An Experimental Comparison of Discrete and Continuous Shape Optimization Methods
TLDR
A quantitative comparison of the reconstruction accuracy and computation times is presented which allows to assess some of the strengths and limitations of both approaches and a novel method to approximate length regularity in a graph cut based framework. Expand
...
1
2
3
4
5
...