LIFT: Learned Invariant Feature Transform

03/30/2016
by   Kwang Moo Yi, et al.
0

We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description. While previous works have successfully tackled each one of these problems individually, we show how to learn to do all three in a unified manner while preserving end-to-end differentiability. We then demonstrate that our Deep pipeline outperforms state-of-the-art methods on a number of benchmark datasets, without the need of retraining.

READ FULL TEXT

page 2

page 6

page 12

page 13

research
04/17/2019

LO-Net: Deep Real-time Lidar Odometry

We present a novel deep convolutional network pipeline, LO-Net, for real...
research
09/07/2017

FingerNet: An Unified Deep Network for Fingerprint Minutiae Extraction

Minutiae extraction is of critical importance in automated fingerprint r...
research
06/03/2019

RF-Net: An End-to-End Image Matching Network based on Receptive Field

This paper proposes a new end-to-end trainable matching network based on...
research
05/27/2017

Deep Matching and Validation Network -- An End-to-End Solution to Constrained Image Splicing Localization and Detection

Image splicing is a very common image manipulation technique that is som...
research
10/29/2020

An End to End Network Architecture for Fundamental Matrix Estimation

In this paper, we present a novel end-to-end network architecture to est...
research
05/07/2019

A deep learning approach for analyzing the composition of chemometric data

We propose novel deep learning based chemometric data analysis technique...
research
07/12/2022

Learning from Label Relationships in Human Affect

Human affect and mental state estimation in an automated manner, face a ...

Please sign up or login with your details

Forgot password? Click here to reset