Homographic Navigation: Geometry-Driven Camera Guidance for Deterministic Planar Capture

• URL: http://arxiv.org/abs/2606.22834v1
• Date: Mon, 22 Jun 2026 04:15:08 GMT
• Title: Homographic Navigation: Geometry-Driven Camera Guidance for Deterministic Planar Capture
• Abstract summary: Homographic navigation is a geometry-centric framework for guiding camera acquisition toward precise capture of planar regions.<n>We generate unlimited synthetic training data via homographic augmentation and train a single-shot model for joint recognition and localization.<n> Experimental results demonstrate that accurate planar alignment can be achieved from minimal supervision.
• Score: 0.9036844836403516
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present homographic navigation, a geometry-centric framework for guiding camera acquisition toward precise capture of planar regions. Rather than treating homography as an output, we use it as an organizing variable that unifies learning, alignment, and evaluation. From a single annotated reference image, we generate unlimited synthetic training data via homographic augmentation and train a single-shot model for joint recognition and localization of multiple artifacts (physical objects with a rectangular planar target) through sparse keypoint prediction. To address precision under limited model input resolution, we introduce a two-pass inference scheme with global detection followed by localized refinement, and a Stable Warp training strategy that significantly improves accuracy, particularly in the high-precision regime. The model also predicts confidence estimates per predicted keypoint and per the whole sample. Experimental results demonstrate that accurate planar alignment can be achieved from minimal supervision, providing a foundation for geometry-driven camera guidance and future learning from in-the-wild video data.

Related papers

• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry [52.232826445242644]
  FoundationGeo bridges relative and metric prediction via spatial calibration and principled data design.<n>Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3.<n>Stage 2 moves beyond global scaling by introducing pixel-wise calibration fields for metric estimation.
  arXiv  Detail & Related papers  (2026-07-13T14:10:01Z)
• Geo-Align: Video Generation Alignment via Metric Geometry Reward [53.65904111864641]
  Geo-Align is the first Reinforcement Learning framework specifically designed for camera-controlled video re-rendering.<n>Built upon a pretrained model, we optimize the model through a scale-aware perceptual reward mechanism.<n>Experiments demonstrate that Geo-Align consistently outperforms existing supervised learning baselines in both precise camera controllability and visual fidelity.
  arXiv  Detail & Related papers  (2026-05-22T17:59:43Z)
• Analytical Modeling and Correction of Distance Error in Homography-Based Ground-Plane Mapping [0.0]
  This paper derives an explicit relationship between homography perturbations and the resulting distance error, showing that the error grows approximately quadratically with the true distance from the camera.<n>A large-scale simulation study with more than 19 million test samples demonstrates that regression achieves higher peak accuracy when the model is reliably fitted.<n>This suggests that improving geometric calibration may yield greater performance gains than increasing model complexity in many practical systems.
  arXiv  Detail & Related papers  (2026-04-12T20:33:09Z)
• HOLO: Homography-Guided Pose Estimator Network for Fine-Grained Visual Localization on SD Maps [13.643067075619841]
  We propose a novel homography-guided pose estimator network for fine-grained visual localization between multi-view images and standard-definition (SD) maps.<n>To the best of our knowledge, this is the first work to unify BEV semantic reasoning with homography learning for image-to-map localization.
  arXiv  Detail & Related papers  (2026-01-06T05:48:47Z)
• ShelfRectNet: Single View Shelf Image Rectification with Homography Estimation [0.0]
  We present a deep learning framework that predicts a 4-point parameterized homography matrix to rectify shelf images captured from arbitrary angles.<n>Our method achieves a mean corner error of 1.298 pixels on the test set.<n>To encourage further research in this domain, we will make our dataset, ShelfRectSet, and code publicly available.
  arXiv  Detail & Related papers  (2025-11-25T14:14:17Z)
• Loc$^2$: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matching [80.57282092735991]
  We propose an accurate and interpretable fine-grained cross-view localization method.<n>It estimates the 3 Degrees of Freedom (DoF) pose of a ground-level image by matching its local features with a reference aerial image.<n> Experiments show state-of-the-art accuracy in challenging scenarios such as cross-area testing and unknown orientation.
  arXiv  Detail & Related papers  (2025-09-11T18:52:16Z)
• Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models [79.96917782423219]
  Orient Anything is the first expert and foundational model designed to estimate object orientation in a single image.<n>By developing a pipeline to annotate the front face of 3D objects, we collect 2M images with precise orientation annotations.<n>Our model achieves state-of-the-art orientation estimation accuracy in both rendered and real images.
  arXiv  Detail & Related papers  (2024-12-24T18:58:43Z)
• Keypoint-based Stereophotoclinometry for Characterizing and Navigating Small Bodies: A Factor Graph Approach [15.863759076104104]
  This paper proposes the incorporation of techniques from stereophotoclinometry into a keypoint-based structure-from-motion system. The proposed framework is validated on real imagery of the Cornelia crater on Asteroid 4 Vesta.
  arXiv  Detail & Related papers  (2023-12-11T22:23:43Z)
• View Consistent Purification for Accurate Cross-View Localization [59.48131378244399]
  This paper proposes a fine-grained self-localization method for outdoor robotics. The proposed method addresses limitations in existing cross-view localization methods. It is the first sparse visual-only method that enhances perception in dynamic environments.
  arXiv  Detail & Related papers  (2023-08-16T02:51:52Z)
• Towards Zero-Shot Scale-Aware Monocular Depth Estimation [28.42580603643096]
  We introduce ZeroDepth, a novel monocular depth estimation framework capable of predicting metric scale for arbitrary test images. This is achieved by (i) the use of input-level geometric embeddings that enable the network to learn a scale prior to objects, and (ii) decoupling the encoder and decoder stages.
  arXiv  Detail & Related papers  (2023-06-29T18:46:11Z)
• An Adaptive Framework for Learning Unsupervised Depth Completion [59.17364202590475]
  We present a method to infer a dense depth map from a color image and associated sparse depth measurements. We show that regularization and co-visibility are related via the fitness of the model to data and can be unified into a single framework.
  arXiv  Detail & Related papers  (2021-06-06T02:27:55Z)

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.