paper-with-me

홈 › Papers

Distinctive Image Features from Scale-Invariant Keypoints

2004-01-05 · David Lowe

This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.

📄 PDF Abstract BibTeX

Code (2)

kornia/kornia/blob/master/kornia/feature/siftdesc.py pytorch
vlfeat/vlfeat

Tasks

Image RegistrationObjectObject RecognitionPatch Matching

Similar Papers 제목 키워드 기반

SO(3)-Pose: SO(3)-Equivariance Learning for 6D Object Pose Estimation

2022-08-17 · Haoran Pan, Jun Zhou, Yuanpeng Liu, Xuequan Lu 외

6D pose estimation of rigid objects from RGB-D images is crucial for object grasping and manipulation in robotics. Although RGB channels and the depth (D) channel are often complementary, providing respectively the appea…

6D Pose Estimation6D Pose Estimation using RGBObjectPose Estimation+1

Learning to Match 2D Keypoints Across Preoperative MR and Intraoperative Ultrasound

2024-09-12 · Hassan Rasheed, Reuben Dorent, Maximilian Fehrentz, Tina Kapur 외

We propose in this paper a texture-invariant 2D keypoints descriptor specifically designed for matching preoperative Magnetic Resonance (MR) images with intraoperative Ultrasound (US) images. We introduce a matching-by-s…

Towards Keypoint Guided Self-Supervised Depth Estimation

2020-11-05 · Kristijan Bartol, David Bojanic, Tomislav Petkovic, Tomislav Pribanic 외

This paper proposes to use keypoints as a self-supervision clue for learning depth map estimation from a collection of input images. As ground truth depth from real images is difficult to obtain, there are many unsupervi…

Depth Estimation

From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery

2022-05-31 · Dimitrios Mallis, Enrique Sanchez, Matt Bell, Georgios Tzimiropoulos

This paper proposes a novel paradigm for the unsupervised learning of object landmark detectors. Contrary to existing methods that build on auxiliary tasks such as image generation or equivariance, we propose a self-trai…

Contrastive LearningImage Generation

A Fast Keypoint Based Hybrid Method for Copy Move Forgery Detection

2016-12-11 · Sunil Kumar, J. V. Desai, Shaktidev Mukherjee

Copy move forgery detection in digital images has become a very popular research topic in the area of image forensics. Due to the availability of sophisticated image editing tools and ever increasing hardware capabilitie…

Image ForensicsKeypoint Detection