ASLFeat: Learning Local Features of Accurate Shape and Localization
- URL: http://arxiv.org/abs/2003.10071v2
- Date: Sun, 19 Apr 2020 12:47:53 GMT
- Title: ASLFeat: Learning Local Features of Accurate Shape and Localization
- Authors: Zixin Luo, Lei Zhou, Xuyang Bai, Hongkai Chen, Jiahui Zhang, Yao Yao,
Shiwei Li, Tian Fang, Long Quan
- Abstract summary: We present ASLFeat, with three light-weight yet effective modifications to mitigate above issues.
First, we resort to deformable convolutional networks to densely estimate and apply local transformation.
Second, we take advantage of the inherent feature hierarchy to restore spatial resolution and low-level details for accurate keypoint localization.
- Score: 42.70030492742363
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This work focuses on mitigating two limitations in the joint learning of
local feature detectors and descriptors. First, the ability to estimate the
local shape (scale, orientation, etc.) of feature points is often neglected
during dense feature extraction, while the shape-awareness is crucial to
acquire stronger geometric invariance. Second, the localization accuracy of
detected keypoints is not sufficient to reliably recover camera geometry, which
has become the bottleneck in tasks such as 3D reconstruction. In this paper, we
present ASLFeat, with three light-weight yet effective modifications to
mitigate above issues. First, we resort to deformable convolutional networks to
densely estimate and apply local transformation. Second, we take advantage of
the inherent feature hierarchy to restore spatial resolution and low-level
details for accurate keypoint localization. Finally, we use a peakiness
measurement to relate feature responses and derive more indicative detection
scores. The effect of each modification is thoroughly studied, and the
evaluation is extensively conducted across a variety of practical scenarios.
State-of-the-art results are reported that demonstrate the superiority of our
methods.
Related papers
- Gaussian Splatting with Localized Points Management [52.009874685460694]
Localized Point Management (LPM) is capable of identifying those error-contributing zones in the highest demand for both point addition and geometry calibration.
LPM applies point densification in the identified zone, whilst resetting the opacity of those points residing in front of these regions so that a new opportunity is created to correct ill-conditioned points.
Notably, LPM improves both vanilla 3DGS and SpaceTimeGS to achieve state-of-the-art rendering quality while retaining real-time speeds.
arXiv Detail & Related papers (2024-06-06T16:55:07Z) - Learning to Produce Semi-dense Correspondences for Visual Localization [11.415451542216559]
This study addresses the challenge of performing visual localization in demanding conditions such as night-time scenarios, adverse weather, and seasonal changes.
We propose a novel method that extracts reliable semi-dense 2D-3D matching points based on dense keypoint matches.
The network utilizes both geometric and visual cues to effectively infer 3D coordinates for unobserved keypoints from the observed ones.
arXiv Detail & Related papers (2024-02-13T10:40:10Z) - PotholeGuard: A Pothole Detection Approach by Point Cloud Semantic
Segmentation [0.0]
3D Semantic Pothole research often overlooks point cloud sparsity, leading to suboptimal local feature capture and segmentation accuracy.
Our model efficiently identifies hidden features and uses a feedback mechanism to enhance local characteristics.
Our approach offers a promising solution for robust and accurate 3D pothole segmentation, with applications in road maintenance and safety.
arXiv Detail & Related papers (2023-11-05T12:57:05Z) - DETR Doesn't Need Multi-Scale or Locality Design [69.56292005230185]
This paper presents an improved DETR detector that maintains a "plain" nature.
It uses a single-scale feature map and global cross-attention calculations without specific locality constraints.
We show that two simple technologies are surprisingly effective within a plain design to compensate for the lack of multi-scale feature maps and locality constraints.
arXiv Detail & Related papers (2023-08-03T17:59:04Z) - Enhancing Deformable Local Features by Jointly Learning to Detect and
Describe Keypoints [8.390939268280235]
Local feature extraction is a standard approach in computer vision for tackling important tasks such as image matching and retrieval.
We propose DALF, a novel deformation-aware network for jointly detecting and describing keypoints.
Our approach also enhances the performance of two real-world applications: deformable object retrieval and non-rigid 3D surface registration.
arXiv Detail & Related papers (2023-04-02T18:01:51Z) - Shared Coupling-bridge for Weakly Supervised Local Feature Learning [0.7366405857677226]
This paper focuses on promoting the currently popular sparse local feature learning with camera pose supervision.
It proposes a Shared Coupling-bridge scheme with four light-weight yet effective improvements for weakly-supervised local feature learning.
It could often obtain a state-of-the-art performance on classic image matching and visual localization.
arXiv Detail & Related papers (2022-12-14T05:47:52Z) - Point Discriminative Learning for Unsupervised Representation Learning
on 3D Point Clouds [54.31515001741987]
We propose a point discriminative learning method for unsupervised representation learning on 3D point clouds.
We achieve this by imposing a novel point discrimination loss on the middle level and global level point features.
Our method learns powerful representations and achieves new state-of-the-art performance.
arXiv Detail & Related papers (2021-08-04T15:11:48Z) - PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image
Segmentation [87.50205728818601]
We propose a PriorGuided Local (PGL) self-supervised model that learns the region-wise local consistency in the latent feature space.
Our PGL model learns the distinctive representations of local regions, and hence is able to retain structural information.
arXiv Detail & Related papers (2020-11-25T11:03:11Z) - 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)
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.