Cross-Descriptor Visual Localization and Mapping
- URL: http://arxiv.org/abs/2012.01377v1
- Date: Wed, 2 Dec 2020 18:19:51 GMT
- Title: Cross-Descriptor Visual Localization and Mapping
- Authors: Mihai Dusmanu, Ondrej Miksik, Johannes L. Sch\"onberger, Marc
Pollefeys
- Abstract summary: Visual localization and mapping is the key technology underlying the majority of Mixed Reality and robotics systems.
We present three novel scenarios for localization and mapping which require the continuous update of feature representations.
Our data-driven approach is agnostic to the feature descriptor type, has low computational requirements, and scales linearly with the number of description algorithms.
- Score: 81.16435356103133
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Visual localization and mapping is the key technology underlying the majority
of Mixed Reality and robotics systems. Most state-of-the-art approaches rely on
local features to establish correspondences between images. In this paper, we
present three novel scenarios for localization and mapping which require the
continuous update of feature representations and the ability to match across
different feature types. While localization and mapping is a fundamental
computer vision problem, the traditional setup treats it as a single-shot
process using the same local image features throughout the evolution of a map.
This assumes the whole process is repeated from scratch whenever the underlying
features are changed. However, reiterating it is typically impossible in
practice, because raw images are often not stored and re-building the maps
could lead to loss of the attached digital content. To overcome the limitations
of current approaches, we present the first principled solution to
cross-descriptor localization and mapping. Our data-driven approach is agnostic
to the feature descriptor type, has low computational requirements, and scales
linearly with the number of description algorithms. Extensive experiments
demonstrate the effectiveness of our approach on state-of-the-art benchmarks
for a variety of handcrafted and learned features.
Related papers
- Generalizable Person Re-Identification via Viewpoint Alignment and
Fusion [74.30861504619851]
This work proposes to use a 3D dense pose estimation model and a texture mapping module to map pedestrian images to canonical view images.
Due to the imperfection of the texture mapping module, the canonical view images may lose the discriminative detail clues from the original images.
We show that our method can lead to superior performance over the existing approaches in various evaluation settings.
arXiv Detail & Related papers (2022-12-05T16:24:09Z) - Investigating the Role of Image Retrieval for Visual Localization -- An
exhaustive benchmark [46.166955777187816]
This paper focuses on understanding the role of image retrieval for multiple visual localization paradigms.
We introduce a novel benchmark setup and compare state-of-the-art retrieval representations on multiple datasets.
Using these tools and in-depth analysis, we show that retrieval performance on classical landmark retrieval or place recognition tasks correlates only for some but not all paradigms to localization performance.
arXiv Detail & Related papers (2022-05-31T12:59:01Z) - CAMERAS: Enhanced Resolution And Sanity preserving Class Activation
Mapping for image saliency [61.40511574314069]
Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input.
We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors.
arXiv Detail & Related papers (2021-06-20T08:20:56Z) - Unsupervised Metric Relocalization Using Transform Consistency Loss [66.19479868638925]
Training networks to perform metric relocalization traditionally requires accurate image correspondences.
We propose a self-supervised solution, which exploits a key insight: localizing a query image within a map should yield the same absolute pose, regardless of the reference image used for registration.
We evaluate our framework on synthetic and real-world data, showing our approach outperforms other supervised methods when a limited amount of ground-truth information is available.
arXiv Detail & Related papers (2020-11-01T19:24:27Z) - A cellular automata approach to local patterns for texture recognition [3.42658286826597]
We propose a method for texture descriptors that combines the representation power of complex objects by cellular automata with the known effectiveness of local descriptors in texture analysis.
Our proposal outperforms other classical and state-of-the-art approaches, especially in the real-world problem.
arXiv Detail & Related papers (2020-07-15T03:25:51Z) - Reorganizing local image features with chaotic maps: an application to
texture recognition [0.0]
We propose a chaos-based local descriptor for texture recognition.
We map the image into the three-dimensional Euclidean space, iterate a chaotic map over this three-dimensional structure and convert it back to the original image.
The performance of our method was verified on the classification of benchmark databases and in the identification of Brazilian plant species based on the texture of the leaf surface.
arXiv Detail & Related papers (2020-07-15T03:15:01Z) - Geometrically Mappable Image Features [85.81073893916414]
Vision-based localization of an agent in a map is an important problem in robotics and computer vision.
We propose a method that learns image features targeted for image-retrieval-based localization.
arXiv Detail & Related papers (2020-03-21T15:36:38Z) - Multi-View Optimization of Local Feature Geometry [70.18863787469805]
We address the problem of refining the geometry of local image features from multiple views without known scene or camera geometry.
Our proposed method naturally complements the traditional feature extraction and matching paradigm.
We show that our method consistently improves the triangulation and camera localization performance for both hand-crafted and learned local features.
arXiv Detail & Related papers (2020-03-18T17:22:11Z) - UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description
without Local Correspondence Supervision [16.68130648568593]
Three related tasks, namely keypoint detection, description, and image retrieval can be jointly tackled using a single unified framework.
By leveraging diverse information from sequential layers of a standard ResNet-based architecture, we are able to extract keypoints and descriptors that encode local information.
Global information for image retrieval is encoded in an end-to-end pipeline, based on pooling of the aforementioned local responses.
arXiv Detail & Related papers (2020-01-20T21:01:38Z)
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.