Publications by Kwang Moo Yi | EPFL Graph Search

Related publications (18)

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

Pascal Fua, Mathieu Salzmann, Kwang Moo Yi, Yinlin Hu, Zheng Dang

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be tackled by solving a linear least-square problem, which can be done by finding the eigenvector corresponding to the smal ...

IEEE COMPUTER SOC2021

A Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Images

Pascal Fua, Vincent Lepetit, Kwang Moo Yi, Alberto Crivellaro, Yannick Verdie

We present a method that estimates in real-time and under challenging conditions the 3D pose of a known object. Our method relies only on grayscale images since depth cameras fail on metallic objects; it can handle poorly textured objects, and cluttered, c ...

2015

Development of a Localization System Based on VLC Technique for an Indoor Environment

Kwang Moo Yi

In this paper, we develop an indoor localization device which embeds localization information into indoor light-emitting-diodes (LED) lighting systems. The key idea of our device is the use of the newly proposed "bit stuffing method". Through the use of st ...

Korean Inst Electr Eng2015

[DEMO] Tracking Texture-less, Shiny Objects with Descriptor Fields

Pascal Fua, Vincent Lepetit, Kwang Moo Yi, Alberto Crivellaro, Yannick Verdie

Our demo demonstrates the method we published at CVPR this year for tracking specular and poorly textured objects, and lets the visitors experiment with it and with their own patterns. Our approach only requires a standard monocular camera (no need for a d ...

2014

Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses

Pascal Fua, Mathieu Salzmann, Kwang Moo Yi, Yinlin Hu, Zheng Dang

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by ﬁnding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear sy ...

2018

Learning to Find Good Correspondences

Pascal Fua, Mathieu Salzmann, Vincent Lepetit, Kwang Moo Yi, Eduard Trulls Fortuny

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outlie ...

2018

Learning to Assign Orientations to Feature Points

Pascal Fua, Vincent Lepetit, Kwang Moo Yi, Yannick Verdie

We show how to train a Convolutional Neural Network to assign a canonical orientation to feature points given an image patch centered on the feature point. Our method improves feature point matching upon the state-of-the art and can be used in conjunction ...

2016

Method, system, and device for learned invariant feature transform for computer images

Pascal Fua, Vincent Lepetit, Kwang Moo Yi, Eduard Trulls Fortuny

A method for training a feature detector of an image processing device, including the steps of detecting features in the image to generate a score map, computing a center of mass on the score map to generate a location, extracting a patch from the image at ...

2018

TILDE: A Temporally Invariant Learned DEtector

Pascal Fua, Vincent Lepetit, Kwang Moo Yi, Yannick Verdie

We introduce a learning-based approach to detect repeatable keypoints under drastic imaging changes of weather and lighting conditions to which state-of-the-art keypoint detectors are surprisingly sensitive. We first identify good keypoint candidates in mu ...

2015

Learning Lightprobes for Mixed Reality Illumination

Pascal Fua, Vincent Lepetit, Kwang Moo Yi

This paper presents the first photometric registration pipeline for Mixed Reality based on high quality illumination estimation by convolutional neural network (CNN) methods. For easy adaptation and deployment of the system, we train the CNN using purely s ...

2017

Beyond Cartesian Representations for Local Descriptors

Patrick Winfried Josef Ebel, Pascal Fua, Kwang Moo Yi, Eduard Trulls Fortuny, Anastasiia Mishchuk

The dominant approach for learning local patch descriptors relies on small image regions whose scale must be properly estimated a priori by a keypoint detector. In other words, if two patches are not in correspondence, their descriptors will not match. A s ...

IEEE COMPUTER SOC2019

Image Matching Across Wide Baselines: From Paper to Practice

Pascal Fua, Kwang Moo Yi, Eduard Trulls Fortuny, Anastasiia Mishchuk

We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task-the accuracy of the reconstructed camera pose-as our primary metric. Our pipeline's modular structure allows easy integration, confi ...

2021

The Visual Object Tracking VOT2014 Challenge Results

Kwang Moo Yi, Bo Li

The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 38 trackers are presented. The number of tested trackers makes VOT 2014 the ...

Springer-Verlag Berlin2015

Learning to Find Good Correspondences

Pascal Fua, Mathieu Salzmann, Vincent Lepetit, Kwang Moo Yi, Eduard Trulls Fortuny

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outlie ...

IEEE2018

Authoring and Living Next-Generation Location-Based Experiences

Kwang Moo Yi

2015

LF-Net: Learning Local Features from Images

Pascal Fua, Kwang Moo Yi, Eduard Trulls Fortuny

We present a novel deep architecture and a training strategy to learn a local feature pipeline from scratch, using collections of images without the need for human supervision. To do so we exploit depth and relative camera pose cues to create a virtual tar ...

2018

Visual tracking in complex scenes through pixel-wise tri-modeling (vol 26, pg 205, 2015)

Kwang Moo Yi

Springer2015

LIFT: Learned Invariant Feature Transform

Pascal Fua, Vincent Lepetit, Kwang Moo Yi, Eduard Trulls Fortuny

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 individu ...

Springer Int Publishing Ag2016