• Corpus ID: 238198359

PDC-Net+: Enhanced Probabilistic Dense Correspondence Network

@article{Truong2021PDCNetEP,
  title={PDC-Net+: Enhanced Probabilistic Dense Correspondence Network},
  author={Prune Truong and Martin Danelljan and Radu Timofte and Luc Van Gool},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.13912}
}
Establishing robust and accurate correspondences between a pair of images is a long-standing computer vision problem with numerous applications. While classically dominated by sparse methods, emerging dense approaches offer a compelling alternative paradigm that avoids the keypoint detection step. However, dense flow estimation is often inaccurate in the case of large displacements, occlusions, or homogeneous regions. In order to apply dense methods to real-world applications, such as pose… 
[PDF] Semantic Reader
7 Citations
Highly Influential Citations
1
Background Citations
2
Methods Citations
6
Results Citations
1

7 Citations

DKM: Dense Kernelized Feature Matching for Geometry Estimation

This paper considers the dense approach instead of the more common sparse paradigm, thus striv-ing to all correspondences, and sets a new state-of-the-art on multiple geometry estimation benchmarks.

Deep Kernelized Dense Geometric Matching

This work formulates dense global matching as a probabilistic regression task using deep kernels, in contrast to typical correlation volume processing, and shows that replacing local correlation with warped feature stacking in the refinement stage further boosts performance.

Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences

We propose Probabilistic Warp Consistency, a weakly-supervised learning objective for semantic matching. Our approach directly supervises the dense matching scores predicted by the network, encoded…

SPARF: Neural Radiance Fields from Sparse and Noisy Poses

This work introduces Sparse Pose Adjusting Radiance Field (SPARF), to address the challenge of novel-view synthesis given only few wide-baseline input images with noisy camera poses, and sets a new state of the art in the sparse-view regime on multiple challenging datasets.

ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer

ASpanFormer, a Transformer-based detector-free matcher that is built on hierarchical attention structure, adopting a novel attention operation which is capable of adjusting attention span in a self-adaptive manner is proposed.

Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions

Refign is a generic extension to self-training-based UDA methods which leverages cross-domain correspondences and introduces no extra training parameters, minimal computational overhead—during training only—and can be used as a drop-in extension to improve any given self-trained UDA method.

Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization

The proposed strategy explicitly prevents the model from pushing away potential candidates in the early stage, and thus improves the recall rate, on the three public datasets, i.e. , FashionIQ, Fashion200k, and Shoes.

References

SHOWING 1-10 OF 113 REFERENCES

Learning Accurate Dense Correspondences and When to Trust Them

This work aims to estimate a dense flow field relating two images, coupled with a robust pixel-wise confidence map indicating the reliability and accuracy of the prediction, and develops a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty.

GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences

This work proposes a universal network architecture that is directly applicable to all the aforementioned dense correspondence problems, and achieves both high accuracy and robustness to large displacements by investigating the combined use of global and local correlation layers.

Neighbourhood Consensus Networks

An end-to-end trainable convolutional neural network architecture that identifies sets of spatially consistent matches by analyzing neighbourhood consensus patterns in the 4D space of all possible correspondences between a pair of images without the need for a global geometric model is developed.

DGC-Net: Dense Geometric Correspondence Network

This paper proposes a coarse-to-fine CNN-based framework that can leverage the advantages of optical flow approaches and extend them to the case of large transformations providing dense and subpixel accurate estimates and proves that the model outperforms existing dense approaches.

COTR: Correspondence Transformer for Matching Across Images

A novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence in the other, yielding a multiscale pipeline able to provide highly-accurate correspondences.

S2DNet: Learning Image Features for Accurate Sparse-to-Dense Matching

S2DNet is introduced, a novel feature matching pipeline designed and trained to efficiently establish both robust and accurate correspondences, and achieves state-of-theart results on the HPatches benchmark, as well as on several long-term visual localization datasets.

Learning Two-View Correspondences and Geometry Using Order-Aware Network

This paper proposes Order-Aware Network, which infers the probabilities of correspondences being inliers and regresses the relative pose encoded by the essential matrix, and is built hierarchically and comprises three novel operations.

Hierarchical Discrete Distribution Decomposition for Match Density Estimation

Hierarchical Discrete Distribution Decomposition (HD^3), a framework suitable for learning probabilistic pixel correspondences in both optical flow and stereo matching, is proposed and achieves state-of-the-art results.

Learning to Find Good Correspondences

A novel normalization technique, called Context Normalization, is introduced, which allows the network to process each data point separately while embedding global information in it, and also makes the network invariant to the order of the correspondences.

D2D: Learning to find good correspondences for image matching and manipulation

A simple approach to determining correspondences between image pairs under large changes in illumination, viewpoint, context, and material and can be used to achieve state of the art or competitive results on a wide range of tasks: local matching, camera localization, 3D reconstruction, and image stylization.
...