mlsanityData to 7 Oct 2026

Object-Guided Day-Night Visual Localization in Urban Scenes

arXiv 2202.04445 ↗First posted 9 Feb 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

We introduce Object-Guided Localization (OGuL) based on a novel method of local-feature matching. Direct matching of local features is sensitive to significant changes in illumination. In contrast, object detection often survives severe changes in lighting conditions. The proposed method first detects semantic objects and establishes correspondences of those objects between images. Object correspondences provide local coarse alignment of the images in the form of a planar homography. These homographies are consequently used to guide the matching of local features. Experiments on standard urban localization datasets (Aachen, Extended-CMU-Season, RobotCar-Season) show that OGuL significantly improves localization results with as simple local features as SIFT, and its performance competes with the state-of-the-art CNN-based methods trained for day-to-night localization.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 67 references that are in the map. First posted on arXiv 9 Feb 2022.

Builds on

24 of 67 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  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. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  6. 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 542
  7. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  8. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 206
  9. 2017Learning to Find Good Correspondencescited by 176
  10. 2019Learning Two-View Correspondences and Geometry Using Order-Aware Networkcited by 148
  11. 2017Convolutional neural network architecture for geometric matchingcited by 138
  12. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
12 more
  1. 2019Neural-Guided RANSAC: Learning Where to Sample Model Hypothesescited by 129
  2. 2020Patch2Pix: Epipolar-Guided Pixel-Level Correspondencescited by 128
  3. 2017End-to-end weakly-supervised semantic alignmentcited by 60
  4. 2015Proposal Flowcited by 57
  5. 2017SCNet: Learning Semantic Correspondencecited by 48
  6. 2020RANSAC-Flow: generic two-stage image alignmentcited by 48
  7. 2017Proposal Flow: Semantic Correspondences from Object Proposalscited by 46
  8. 2020Deep Hough-Transform Line Priorscited by 44
  9. 2017FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondencecited by 42
  10. 2018Structure-from-Motion using Dense CNN Features with Keypoint Relocalizationcited by 9
  11. 2020Learning to Guide Local Feature Matchescited by 6
  12. 2018Matching Disparate Image Pairs Using Shape-Aware ConvNetscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2024Maps from Motion (MfM): Generating 2D Semantic Maps from Sparse Multi-view Imagescited by 1
  2. 20233DoF Localization from a Single Image and an Object Map: the Flatlandia Problem and Datasetcited by 0