Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction

@article{Cheng2014FastAA,
  title={Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction},
  author={Jian Cheng and Cong Leng and Jiaxiang Wu and Hainan Cui and Hanqing Lu},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={1-8}
}
  • Jian Cheng, Cong Leng, +2 authors Hanqing Lu
  • Published 2014
  • Mathematics, Computer Science
  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
Image matching is one of the most challenging stages in 3D reconstruction, which usually occupies half of computational cost and inaccurate matching may lead to failure of reconstruction. Therefore, fast and accurate image matching is very crucial for 3D reconstruction. In this paper, we proposed a Cascade Hashing strategy to speed up the image matching. In order to accelerate the image matching, the proposed Cascade Hashing method is designed to be three-layer structure: hashing lookup… Expand
GPU Accelerated Cascade Hashing Image Matching for Large Scale 3D Reconstruction
TLDR
A GPU accelerated image matching method with improved Cascade Hashing is proposed, and the ep bipolar constraint is introduced, and use the epipolar geometry to guide the feature matching procedure, which further reduces the matching cost. Expand
GPU Accelerated Image Matching with Cascade Hashing
TLDR
This paper proposes a disk-memory-GPU data exchange strategy and optimize the load order of data, so that the proposed method can deal with big data, and parallelizes the Cascade Hashing method on GPU. Expand
Parallel K Nearest Neighbor Matching for 3D Reconstruction
TLDR
A new feature tacking method working in a parallel manner rather than in a single thread scheme that is able to rapidly match a big volume of keypoints and avoids to consume high computation time, then yielding a set of correct correspondences. Expand
Parallel and efficient approximate nearest patch matching for image editing applications
TLDR
A novel GPU-based patch matching method which efficiently finds approximate nearest neighbor correspondences for patches between images by reducing the search space of patch direction by estimating a coherent feature direction field for each image and computing the similarity between patches with a direction-aware alignment scheme. Expand
Do We Need Binary Features for 3D Reconstruction?
  • Bin Fan, Qingqun Kong, +5 authors P. Fua
  • Computer Science, Mathematics
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2016
TLDR
It is revealed that not all binary features are capable of 3D reconstruction and most of them are inferior to the classical SIFT based method in terms of reconstruction accuracy and completeness with a not significant better computational performance. Expand
Do We Need Binary Features for 3 D Reconstruction ?
Binary features have been incrementally popular in the past few years due to their low memory footprints and the efficient computation of Hamming distance between binary descriptors. They have beenExpand
A Full Density Stereo Matching System Based on the Combination of CNNs and Slanted-Planes
TLDR
A convolutional neural network (CNN) based cost estimation method for computing the similarity of image patches and results indicate superior generalization capability of the method than other supervised learning methods. Expand
Geometry-Aware Feature Matching for Structure from Motion Applications
TLDR
A two-stage, geometry-aware approach for matching SIFT-like features in a fast and reliable manner that prevents pre-emptive rejection using a selective ratio-test and works effectively even on scenes with repetitive structures. Expand
On-Device Scalable Image-Based Localization via Prioritized Cascade Search and Fast One-Many RANSAC
TLDR
This work presents the design of an entire on-device system for large-scale urban localization using images, and proposes a new hashing-based cascade search for fast computation of 2D–3D correspondences and a new one-many RANSAC for accurate pose estimation. Expand
Real-time video fusion based on multistage hashing and hybrid transformation with depth adjustment
TLDR
This work proposes multistage hashing to find matched feature-point pairs from coarse to fine, and builds hybrid transformation with depth adjustment to tackle the distortion and scene depth variation of multiview frames in videos. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 22 REFERENCES
Kernelized locality-sensitive hashing for scalable image search
  • B. Kulis, K. Grauman
  • Mathematics, Computer Science
  • 2009 IEEE 12th International Conference on Computer Vision
  • 2009
TLDR
It is shown how to generalize locality-sensitive hashing to accommodate arbitrary kernel functions, making it possible to preserve the algorithm's sub-linear time similarity search guarantees for a wide class of useful similarity functions. Expand
LDAHash: Improved Matching with Smaller Descriptors
TLDR
This work reduces the size of the descriptors by representing them as short binary strings and learn descriptor invariance from examples, and shows extensive experimental validation, demonstrating the advantage of the proposed approach. Expand
Fast image search for learned metrics
TLDR
A method that enables scalable image search for learned metrics and an indirect solution that enables metric learning and hashing for vector spaces whose high dimensionality make it infeasible to learn an explicit weighting over the feature dimensions is introduced. Expand
Speeded-Up Robust Features (SURF)
TLDR
A novel scale- and rotation-invariant detector and descriptor, coined SURF (Speeded-Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster. Expand
Building Rome in a day
TLDR
A system that can match and reconstruct 3D scenes from extremely large collections of photographs such as those found by searching for a given city on Internet photo sharing sites and is designed to scale gracefully with both the size of the problem and the amount of available computation. Expand
Accurate, Dense, and Robust Multiview Stereopsis
TLDR
A novel algorithm for multiview stereopsis that outputs a dense set of small rectangular patches covering the surfaces visible in the images, which outperforms all others submitted so far for four out of the six data sets. Expand
Locality-sensitive hashing scheme based on p-stable distributions
TLDR
A novel Locality-Sensitive Hashing scheme for the Approximate Nearest Neighbor Problem under lp norm, based on p-stable distributions that improves the running time of the earlier algorithm and yields the first known provably efficient approximate NN algorithm for the case p<1. Expand
A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms
TLDR
This paper first survey multi-view stereo algorithms and compare them qualitatively using a taxonomy that differentiates their key properties, then describes the process for acquiring and calibrating multiview image datasets with high-accuracy ground truth and introduces the evaluation methodology. Expand
Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration
TLDR
A system that answers the question, “What is the fastest approximate nearest-neighbor algorithm for my data?” and a new algorithm that applies priority search on hierarchical k-means trees, which is found to provide the best known performance on many datasets. Expand
Scalable Recognition with a Vocabulary Tree
  • D. Nistér, Henrik Stewénius
  • Computer Science
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
TLDR
A recognition scheme that scales efficiently to a large number of objects and allows a larger and more discriminatory vocabulary to be used efficiently is presented, which it is shown experimentally leads to a dramatic improvement in retrieval quality. Expand
...
1
2
3
...