Multiple-Kernel Local-Patch Descriptor

07/25/2017
by   Arun Mukundan, et al.
0

We propose a multiple-kernel local-patch descriptor based on efficient match kernels of patch gradients. It combines two parametrizations of gradient position and direction, each parametrization provides robustness to a different type of patch miss-registration: polar parametrization for noise in the patch dominant orientation detection, Cartesian for imprecise location of the feature point. Even though handcrafted, the proposed method consistently outperforms the state-of-the-art methods on two local patch benchmarks.

READ FULL TEXT

page 6

page 7

research
11/27/2018

Understanding and Improving Kernel Local Descriptors

We propose a multiple-kernel local-patch descriptor based on efficient m...
research
04/15/2019

Explicit Spatial Encoding for Deep Local Descriptors

We propose a kernelized deep local-patch descriptor based on efficient m...
research
06/08/2016

Rotation Invariant Angular Descriptor Via A Bandlimited Gaussian-like Kernel

We present a new smooth, Gaussian-like kernel that allows the kernel den...
research
08/01/2023

A Majority Invariant Approach to Patch Robustness Certification for Deep Learning Models

Patch robustness certification ensures no patch within a given bound on ...
research
12/16/2020

Learning to Recognize Patch-Wise Consistency for Deepfake Detection

We propose to detect Deepfake generated by face manipulation based on on...
research
03/22/2018

PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction

We introduce a novel RGB-D patch descriptor designed for detecting copla...
research
10/10/2013

From Shading to Local Shape

We develop a framework for extracting a concise representation of the sh...

Please sign up or login with your details

Forgot password? Click here to reset