paper-with-me

홈 › Papers

BOLD - Binary Online Learned Descriptor For Efficient Image Matching

2015-06-01 · CVPR 2015 6 · Vassileios Balntas, Lilian Tang, Krystian Mikolajczyk

In this paper we propose a novel approach to generate a binary descriptor optimized for each image patch independently. The approach is inspired by the linear discriminant embedding that simultaneously increases inter and decreases intra class distances. A set of discriminative and uncorrelated binary tests is established from all possible tests in an offline training process. The patch adapted descriptors are then efficiently built online from a subset of tests which lead to lower intra class distances thus a more robust descriptor. A patch descriptor consists of two binary strings where one represents the results of the tests and the other indicates the subset of the patch-related robust tests that are used for calculating a masked Hamming distance. Our experiments on three different benchmarks demonstrate improvements in matching performance, and illustrate that per-patch optimization outperforms global optimization.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

global-optimization

Similar Papers 제목 키워드 기반

DLBD: A Self-Supervised Direct-Learned Binary Descriptor

2023-01-01 · CVPR 2023 1 · Bin Xiao, Yang Hu, Bo Liu, Xiuli Bi 외

For learning-based binary descriptors, the binarization process has not been well addressed. The reason is that the binarization blocks gradient back-propagation. Existing learning-based binary descriptors learn real…

BinarizationImage RetrievalRetrieval

Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence

2016-06-01 · CVPR 2016 6 · Jin Xie, Meng Wang, Yi Fang

Dense 3D shape correspondence is an important problem in computer vision and computer graphics. Recently, the local shape descriptor based 3D shape correspondence approaches have been widely studied, where the local shap…

BIND: Binary Integrated Net Descriptors for Texture-Less Object Recognition

2017-07-01 · CVPR 2017 7 · Jacob Chan, Jimmy Addison Lee, Qian Kemao

This paper presents BIND (Binary Integrated Net Descriptor), a texture-less object detector that encodes multi-layered binary-represented nets for high precision edge-based description. Our proposed concept aligns layers…

ObjectObject Recognition

Scalable Full Flow with Learned Binary Descriptors

2017-07-20 · Gottfried Munda, Alexander Shekhovtsov, Patrick Knöbelreiter, Thomas Pock

We propose a method for large displacement optical flow in which local matching costs are learned by a convolutional neural network (CNN) and a smoothness prior is imposed by a conditional random field (CRF). We tackle t…

Optical Flow Estimation

LATCH: Learned Arrangements of Three Patch Codes

2015-01-15 · Gil Levi, Tal Hassner

We present a novel means of describing local image appearances using binary strings. Binary descriptors have drawn increasing interest in recent years due to their speed and low memory footprint. A known shortcoming of t…