Skip to content

Commit

Permalink
FaVoR WACV draft, with video
Browse files Browse the repository at this point in the history
  • Loading branch information
@viciopoli01
viciopoli01 committed Nov 5, 2024
1 parent e139da6 commit a3f6d3a
Show file tree
Hide file tree
Showing 3 changed files with 24 additions and 83 deletions.
55 changes: 24 additions & 31 deletions _pages/favor.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -5,15 +5,16 @@ subtitle: ""
description: WACV (2025) paper on rendering feature descriptors from unseen views
permalink: /favor/
nav_order: 9984
usemathjax: true
nav_exclude: true
---


[<i class="fa fa-file-text-o" aria-hidden="true"></i> arXiv pre-print ](https://arxiv.org/abs/2409.07571){: .btn .btn-blue }
<!--
[<i class="fa fa-github" aria-hidden="true"></i> View it on Github](https://github.com/utiasSTARS/){: .btn .btn-green }
[<i class="fa fa-newspaper-o" aria-hidden="true"></i> WACV Paper](){: .btn .btn-red }
[<i class="fa fa-newspaper-o" aria-hidden="true"></i> Supplementary](){: .btn .btn-red }

[<i class="fa fa-newspaper-o" aria-hidden="true"></i> WACV Paper](http://papers.starslab.ca/favor){: .btn .btn-red }
[<i class="fa fa-newspaper-o" aria-hidden="true"></i> Supplementary](http://papers.starslab.ca/favor){: .btn .btn-red }
-->

{::nomarkdown}
<div style='text-align:center'>
Expand Down Expand Up @@ -254,7 +255,7 @@ Camera relocalization methods range from dense image alignment to direct camera
<h2 class="portfolio-modal-title">Great Court</h2>
<div class="divider-custom">
<div class="divider-custom-line"></div>
<div class="divider-custom-icon"><i class="fas fa-camera"></i></div>
<div class="divider-custom-icon"><i class="fa fa-camera"></i></div>
<div class="divider-custom-line"></div>
</div>
<p>The video below shows the camera pose relocalization computed using FaVoR. The purple frame indicates the starting camera position provided by the first DenseVLAD result, while the blue frame represents the ground truth camera pose of the query image. The estimated camera pose is shown in black, connected to the initial pose by a green line.</p>
Expand Down Expand Up @@ -284,7 +285,7 @@ Camera relocalization methods range from dense image alignment to direct camera
<h2 class="portfolio-modal-title">King's College</h2>
<div class="divider-custom">
<div class="divider-custom-line"></div>
<div class="divider-custom-icon"><i class="fas fa-camera"></i></div>
<div class="divider-custom-icon"><i class="fa fa-camera"></i></div>
<div class="divider-custom-line"></div>
</div>
<p>The video below shows the camera pose relocalization computed using FaVoR. The purple frame indicates the starting camera position provided by the first DenseVLAD result, while the blue frame represents the ground truth camera pose of the query image. The estimated camera pose is shown in black, connected to the initial pose by a green line.</p>
Expand Down Expand Up @@ -314,7 +315,7 @@ Camera relocalization methods range from dense image alignment to direct camera
<h2 class="portfolio-modal-title">Old Hospital</h2>
<div class="divider-custom">
<div class="divider-custom-line"></div>
<div class="divider-custom-icon"><i class="fas fa-camera"></i></div>
<div class="divider-custom-icon"><i class="fa fa-camera"></i></div>
<div class="divider-custom-line"></div>
</div>
<p>The video below shows the camera pose relocalization computed using FaVoR. The purple frame indicates the starting camera position provided by the first DenseVLAD result, while the blue frame represents the ground truth camera pose of the query image. The estimated camera pose is shown in black, connected to the initial pose by a green line.</p>
Expand Down Expand Up @@ -344,7 +345,7 @@ Camera relocalization methods range from dense image alignment to direct camera
<h2 class="portfolio-modal-title">Shop Facade</h2>
<div class="divider-custom">
<div class="divider-custom-line"></div>
<div class="divider-custom-icon"><i class="fas fa-camera"></i></div>
<div class="divider-custom-icon"><i class="fa fa-camera"></i></div>
<div class="divider-custom-line"></div>
</div>
<p>The video below shows the camera pose relocalization computed using FaVoR. The purple frame indicates the starting camera position provided by the first DenseVLAD result, while the blue frame represents the ground truth camera pose of the query image. The estimated camera pose is shown in black, connected to the initial pose by a green line.</p>
Expand Down Expand Up @@ -374,7 +375,7 @@ Camera relocalization methods range from dense image alignment to direct camera
<h2 class="portfolio-modal-title">St. Mary's Church</h2>
<div class="divider-custom">
<div class="divider-custom-line"></div>
<div class="divider-custom-icon"><i class="fas fa-camera"></i></div>
<div class="divider-custom-icon"><i class="fa fa-camera"></i></div>
<div class="divider-custom-line"></div>
</div>
<p>The video below shows the camera pose relocalization computed using FaVoR. The purple frame indicates the starting camera position provided by the first DenseVLAD result, while the blue frame represents the ground truth camera pose of the query image. The estimated camera pose is shown in black, connected to the initial pose by a green line.</p>
Expand Down Expand Up @@ -410,20 +411,12 @@ Camera relocalization methods range from dense image alignment to direct camera
In the video below, we extract Alike-l features from a target image. We then match the target features with those extracted from a query image under Standard feature matching. On the rigth side, we report the matches in three iterations of the FaVoR method queried from the target image pose. It is noticeble that the amount of matches is much higher in the 3rd iteration of FaVoR compared to the standard matching approach. The text at the bottom left of the image reports the distance in meters and degree between the target image and the query images and the number of matches for both the methods, the text turn out red when the number of standard feature matches is higher than the FaVoR ones.
</p>
<div class="text-center">
<video width='48%' loop autoplay muted controls>
<source src="/assets/favor/video/video_desc_invariance_comp.mp4" alt="feature invariance">
<video width='100%' loop autoplay muted controls>
<source src="/assets/favor/video/video_desc_invariance_comp.webm" alt="feature invariance">
Your browser does not support the video tag.
</video>
</div>

<div class="video-container">
<video width="640" height="360" controls>
<source src="{{ '/assets/favor/video/video_desc_invariance_comp.mp4' | relative_url }}" type="video/mp4">
Your browser does not support the video tag.
</video>
</div>


</br>

<!-- -->
Expand Down Expand Up @@ -835,19 +828,19 @@ In the video below, we extract Alike-l features from a target image. We then mat

<div class="row">
<div class="col">
<a class="btn" href="#"><i class="fas fa-cubes"></i> Great Court Model</a>
<a class="btn" href="#"><i class="fa fa-cubes"></i> Great Court Model</a>
</div>
<div class="col">
<a class="btn" href="#"><i class="fas fa-cubes"></i> King's College Model</a>
<a class="btn" href="#"><i class="fa fa-cubes"></i> King's College Model</a>
</div>
<div class="col">
<a class="btn" href="#"><i class="fas fa-cubes"></i> Old Hospital Model</a>
<a class="btn" href="#"><i class="fa fa-cubes"></i> Old Hospital Model</a>
</div>
<div class="col">
<a class="btn" href="#"><i class="fas fa-cubes"></i> Shop Facade Model</a>
<a class="btn" href="#"><i class="fa fa-cubes"></i> Shop Facade Model</a>
</div>
<div class="col">
<a class="btn" href="#"><i class="fas fa-cubes"></i> St. Mary's Church Model</a>
<a class="btn" href="#"><i class="fa fa-cubes"></i> St. Mary's Church Model</a>
</div>
</div>

Expand All @@ -857,25 +850,25 @@ In the video below, we extract Alike-l features from a target image. We then mat
<!-- Buttons for 7-Scenes Dataset -->
<div class="row">
<div class="col">
<a class="btn" href="#"><i class="fas fa-cubes"></i> Chess Model</a>
<a class="btn" href="#"><i class="fa fa-cubes"></i> Chess Model</a>
</div>
<div class="col">
<a class="btn" href="#"><i class="fas fa-cubes"></i> Fire Model</a>
<a class="btn" href="#"><i class="fa fa-cubes"></i> Fire Model</a>
</div>
<div class="col">
<a class="btn" href="#"><i class="fas fa-cubes"></i> Heads Model</a>
<a class="btn" href="#"><i class="fa fa-cubes"></i> Heads Model</a>
</div>
<div class="col">
<a class="btn" href="#"><i class="fas fa-cubes"></i> Office Model</a>
<a class="btn" href="#"><i class="fa fa-cubes"></i> Office Model</a>
</div>
<div class="col">
<a class="btn" href="#"><i class="fas fa-cubes"></i> Pumpkin Model</a>
<a class="btn" href="#"><i class="fa fa-cubes"></i> Pumpkin Model</a>
</div>
<div class="col">
<a class="btn" href="#"><i class="fas fa-cubes"></i> Red Kitchen Model</a>
<a class="btn" href="#"><i class="fa fa-cubes"></i> Red Kitchen Model</a>
</div>
<div class="col">
<a class="btn" href="#"><i class="fas fa-cubes"></i> Stairs Model</a>
<a class="btn" href="#"><i class="fa fa-cubes"></i> Stairs Model</a>
</div>
</div>

Expand Down
52 changes: 0 additions & 52 deletions assets/favor/scripts.js
View file
Original file line number Diff line number Diff line change
@@ -1,8 +1,3 @@
/*!
* Start Bootstrap - Freelancer v7.0.7 (https://startbootstrap.com/theme/freelancer)
* Copyright 2013-2023 Start Bootstrap
* Licensed under MIT (https://github.com/StartBootstrap/startbootstrap-freelancer/blob/master/LICENSE)
*/
//
// Scripts
//
Expand All @@ -27,53 +22,6 @@ document.addEventListener("DOMContentLoaded", function() {
}
});

window.addEventListener('DOMContentLoaded', event => {

// Navbar shrink function
var navbarShrink = function () {
const navbarCollapsible = document.body.querySelector('#mainNav');
if (!navbarCollapsible) {
return;
}
if (window.scrollY === 0) {
navbarCollapsible.classList.remove('navbar-shrink')
} else {
navbarCollapsible.classList.add('navbar-shrink')
}

};

// Shrink the navbar
navbarShrink();

// Shrink the navbar when page is scrolled
document.addEventListener('scroll', navbarShrink);

// Activate Bootstrap scrollspy on the main nav element
const mainNav = document.body.querySelector('#mainNav');
if (mainNav) {
new bootstrap.ScrollSpy(document.body, {
target: '#mainNav',
rootMargin: '0px 0px -40%',
});
};

// Collapse responsive navbar when toggler is visible
const navbarToggler = document.body.querySelector('.navbar-toggler');
const responsiveNavItems = [].slice.call(
document.querySelectorAll('#navbarResponsive .nav-link')
);
responsiveNavItems.map(function (responsiveNavItem) {
responsiveNavItem.addEventListener('click', () => {
if (window.getComputedStyle(navbarToggler).display !== 'none') {
navbarToggler.click();
}
});
});

});



document.addEventListener('DOMContentLoaded', function() {
// do this for each video element (5 in total)
Expand Down
Binary file renamed ...avor/video/video_desc_invariance_comp.mp4 → ...vor/video/video_desc_invariance_comp.webm
View file
Binary file not shown.

0 comments on commit a3f6d3a

Please sign in to comment.