mlsanityData to 7 Oct 2026

NeuralMarker: A Framework for Learning General Marker Correspondence

arXiv 2209.08896 ↗First posted 19 Sep 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of estimating correspondences from a general marker, such as a movie poster, to an image that captures such a marker. Conventionally, this problem is addressed by fitting a homography model based on sparse feature matching. However, they are only able to handle plane-like markers and the sparse features do not sufficiently utilize appearance information. In this paper, we propose a novel framework NeuralMarker, training a neural network estimating dense marker correspondences under various challenging conditions, such as marker deformation, harsh lighting, etc. Besides, we also propose a novel marker correspondence evaluation method circumstancing annotations on real marker-image pairs and create a new benchmark. We show that NeuralMarker significantly outperforms previous methods and enables new interesting applications, including Augmented Reality (AR) and video editing.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 22 of its 47 references that are in the map. First posted on arXiv 19 Sep 2022.

Builds on

22 of 47 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  3. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  4. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  5. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  6. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  7. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  8. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  9. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  10. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 273
  11. 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
  12. 2017Convolutional neural network architecture for geometric matchingcited by 138
10 more
  1. 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
  2. 2020Learning Feature Descriptors using Camera Pose Supervisioncited by 104
  3. 2018DGC-Net: Dense Geometric Correspondence Networkcited by 67
  4. 2021GAN-Supervised Dense Visual Alignmentcited by 61
  5. 2020RANSAC-Flow: generic two-stage image alignmentcited by 48
  6. 2018Deep ChArUco: Dark ChArUco Marker Pose Estimationcited by 18
  7. 2017ChromaTag: A Colored Marker and Fast Detection Algorithmcited by 11
  8. 2021E2ETag: An End-to-End Trainable Method for Generating and Detecting Fiducial Markerscited by 7
  9. 2016Learnable Visual Markerscited by 5
  10. 2022DeepFormableTag: End-to-end Generation and Recognition of Deformable Fiducial Markerscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 4.

4 papers.

  1. 2023FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimationcited by 114
  2. 2023MFT: Long-Term Tracking of Every Pixelcited by 61
  3. 2023PATS: Patch Area Transportation with Subdivision for Local Feature Matchingcited by 33
  4. 2023Uncertainty-Driven Dense Two-View Structure from Motioncited by 3