Dual-Resolution Correspondence Networks

• URL: http://arxiv.org/abs/2006.08844v2
• Date: Wed, 28 Oct 2020 17:16:58 GMT
• Title: Dual-Resolution Correspondence Networks
• Authors: Xinghui Li, Kai Han, Shuda Li, Victor Adrian Prisacariu
• Abstract summary: We introduce Dual-Resolution Correspondence Networks (DualRC-Net), to obtain pixel-wise correspondences in a coarse-to-fine manner. We evaluate our method on large-scale public benchmarks including HPatches, InLoc, and Aachen Day-Night.
• Score: 20.004691262722265
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We tackle the problem of establishing dense pixel-wise correspondences between a pair of images. In this work, we introduce Dual-Resolution Correspondence Networks (DualRC-Net), to obtain pixel-wise correspondences in a coarse-to-fine manner. DualRC-Net extracts both coarse- and fine- resolution feature maps. The coarse maps are used to produce a full but coarse 4D correlation tensor, which is then refined by a learnable neighbourhood consensus module. The fine-resolution feature maps are used to obtain the final dense correspondences guided by the refined coarse 4D correlation tensor. The selected coarse-resolution matching scores allow the fine-resolution features to focus only on a limited number of possible matches with high confidence. In this way, DualRC-Net dramatically increases matching reliability and localisation accuracy, while avoiding to apply the expensive 4D convolution kernels on fine-resolution feature maps. We comprehensively evaluate our method on large-scale public benchmarks including HPatches, InLoc, and Aachen Day-Night. It achieves the state-of-the-art results on all of them.

Related papers

• Local All-Pair Correspondence for Point Tracking [59.76186266230608]
  We introduce LocoTrack, a highly accurate and efficient model designed for the task of tracking any point (TAP) across video sequences. LocoTrack achieves unmatched accuracy on all TAP-Vid benchmarks and operates at a speed almost 6 times faster than the current state-of-the-art.
  arXiv  Detail & Related papers  (2024-07-22T06:49:56Z)
• Quantity-Aware Coarse-to-Fine Correspondence for Image-to-Point Cloud Registration [4.954184310509112]
  Image-to-point cloud registration aims to determine the relative camera pose between an RGB image and a reference point cloud. Matching individual points with pixels can be inherently ambiguous due to modality gaps. We propose a framework to capture quantity-aware correspondences between local point sets and pixel patches.
  arXiv  Detail & Related papers  (2023-07-14T03:55:54Z)
• Progressive Multi-resolution Loss for Crowd Counting [126.01887803981619]
  We propose to predict the density map at one resolution but measure the density map at multiple resolutions. We mathematically prove it is superior to a single-resolution L2 loss.
  arXiv  Detail & Related papers  (2022-12-08T07:55:13Z)
• Unpaired Image Super-Resolution with Optimal Transport Maps [128.1189695209663]
  Real-world image super-resolution (SR) tasks often do not have paired datasets limiting the application of supervised techniques. We propose an algorithm for unpaired SR which learns an unbiased OT map for the perceptual transport cost. Our algorithm provides nearly state-of-the-art performance on the large-scale unpaired AIM-19 dataset.
  arXiv  Detail & Related papers  (2022-02-02T16:21:20Z)
• High Quality Segmentation for Ultra High-resolution Images [72.97958314291648]
  We propose the Continuous Refinement Model for the ultra high-resolution segmentation refinement task. Our proposed method is fast and effective on image segmentation refinement.
  arXiv  Detail & Related papers  (2021-11-29T11:53:06Z)
• InfinityGAN: Towards Infinite-Resolution Image Synthesis [92.40782797030977]
  We present InfinityGAN, a method to generate arbitrary-resolution images. We show how it trains and infers patch-by-patch seamlessly with low computational resources.
  arXiv  Detail & Related papers  (2021-04-08T17:59:30Z)
• $\mathbb{X}$Resolution Correspondence Networks [15.214155342197474]
  In this paper, we aim at establishing accurate dense correspondences between a pair of images with overlapping field of view under challenging illumination variation, viewpoint changes, and style differences.
  arXiv  Detail & Related papers  (2020-12-17T18:57:58Z)
• Displacement-Invariant Cost Computation for Efficient Stereo Matching [122.94051630000934]
  Deep learning methods have dominated stereo matching leaderboards by yielding unprecedented disparity accuracy. But their inference time is typically slow, on the order of seconds for a pair of 540p images. We propose a emphdisplacement-invariant cost module to compute the matching costs without needing a 4D feature volume.
  arXiv  Detail & Related papers  (2020-12-01T23:58:16Z)
• Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions [41.43309123350792]
  We adopt the recent Neighbourhood Consensus Networks that have demonstrated promising performance for difficult correspondence problems. We propose modifications to overcome their main limitations: large memory consumption, large inference time and poorly localised correspondences. Our proposed modifications can reduce the memory footprint and execution time more than $10times$, with equivalent results.
  arXiv  Detail & Related papers  (2020-04-22T13:37:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.