Correspondence Networks With Adaptive Neighbourhood Consensus

@article{Li2020CorrespondenceNW,
  title={Correspondence Networks With Adaptive Neighbourhood Consensus},
  author={Shuda Li and K. Han and Theo W. Costain and Henry Howard-Jenkins and V. Prisacariu},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={10193-10202}
}
  • Shuda Li, K. Han, +2 authors V. Prisacariu
  • Published 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
In this paper, we tackle the task of establishing dense visual correspondences between images containing objects of the same category. This is a challenging task due to large intra-class variations and a lack of dense pixel level annotations. We propose a convolutional neural network architecture, called adaptive neighbourhood consensus network (ANC-Net), that can be trained end-to-end with sparse key-point annotations, to handle this challenge. At the core of ANC-Net is our proposed non… Expand
8 Citations
Semi-Global Context Network for Semantic Correspondence
  • PDF
Convolutional Hough Matching Networks
  • PDF
D2D: Learning to find good correspondences for image matching and manipulation
  • 7
  • PDF
Hypercorrelation Squeeze for Few-Shot Segmentation
  • Highly Influenced
  • PDF
Dual-Resolution Correspondence Networks
  • 5
  • PDF
GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network
  • 5
  • PDF

References

SHOWING 1-10 OF 39 REFERENCES
Neighbourhood Consensus Networks
  • 100
  • Highly Influential
  • PDF
End-to-End Weakly-Supervised Semantic Alignment
  • 89
  • PDF
PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence
  • 21
  • PDF
Self-supervised Learning for Video Correspondence Flow
  • 32
  • PDF
SCNet: Learning Semantic Correspondence
  • 73
  • PDF
Dynamic Context Correspondence Network for Semantic Alignment
  • 18
  • Highly Influential
  • PDF
Universal Correspondence Network
  • 206
  • Highly Influential
  • PDF
FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence
  • 47
  • Highly Influential
  • PDF
Convolutional Neural Network Architecture for Geometric Matching
  • 256
  • PDF
Hyperpixel Flow: Semantic Correspondence With Multi-Layer Neural Features
  • 25
  • Highly Influential
  • PDF
...
1
2
3
4
...