feat: second day

This commit is contained in:
Laureηt 2023-01-24 17:48:08 +01:00
parent 8f65a57b33
commit 41547c2133
Signed by: Laurent
SSH key fingerprint: SHA256:kZEpW8cMJ54PDeCvOhzreNr4FSh6R13CMGH/POoO8DI
10 changed files with 393 additions and 317 deletions

View file

@ -1,3 +1,4 @@
{ {
"explorer.excludeGitIgnore": true, "explorer.excludeGitIgnore": true,
"latex-workshop.latex.recipe.default": "latexmk (lualatex)"
} }

Binary file not shown.

Before

Width:  |  Height:  |  Size: 13 MiB

After

Width:  |  Height:  |  Size: 9.7 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 7.1 MiB

BIN
assets/deeplight.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.4 MiB

BIN
assets/dir_7_mip2.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 181 KiB

BIN
assets/materials_mip2.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 20 KiB

BIN
src/paper.pdf Normal file

Binary file not shown.

View file

@ -1,11 +1,26 @@
\documentclass[a4paper, 11pt]{article} \documentclass[
\usepackage[T1]{fontenc} 11pt,
\usepackage[utf8]{inputenc} a4paper
\usepackage{graphicx} ]{article}
\usepackage{amsfonts}
\usepackage{color} % Packages
\usepackage[pagebackref,breaklinks,colorlinks]{hyperref} \usepackage{fontspec}
\usepackage{libertinus-otf}
\usepackage[a4paper, hmargin=2cm, vmargin=3cm]{geometry} \usepackage[a4paper, hmargin=2cm, vmargin=3cm]{geometry}
\usepackage{graphicx}
\usepackage{microtype}
\usepackage{amsmath}
% pdfx loads both hyperref and xcolor internally
% \usepackage{hyperref}
% \usepackage{xcolor}
\usepackage[a-3u]{pdfx}
% We use \hypersetup to pass options to hyperref
\hypersetup{
colorlinks = true,
breaklinks = true,
}
\graphicspath{{../assets/}} \graphicspath{{../assets/}}
@ -13,10 +28,9 @@
\title{"Projet Long" Bibliography} \title{"Projet Long" Bibliography}
\author{Laurent Fainsin} \author{Laurent Fainsin}
\date{\the\year-\ifnum\month<10\relax0\fi\the\month-\ifnum\day<10\relax0\fi\the\day} \date{2023-01-24}
\maketitle \maketitle
\newpage
{ {
\hypersetup{hidelinks} \hypersetup{hidelinks}
@ -30,7 +44,7 @@
The field of 3D reconstruction techniques in photography, such as Reflectance Transformation Imaging (RTI)~\cite{giachetti2018} and Photometric Stereo~\cite{durou2020}, often require a precise understanding of the lighting conditions in the scene being captured. One common method for calibrating the lighting is to include one or more spheres in the scene, as shown in the left example of Figure~\ref{fig:intro}. However, manually outlining these spheres can be tedious and time-consuming, especially in the field of visual effects where the presence of chrome spheres is prevalent~\cite{jahirul_grey_2021}. This task can be made more efficient by using deep learning methods for detection. The goal of this project is to develop a neural network that can accurately detect both matte and shiny spheres in a scene. The field of 3D reconstruction techniques in photography, such as Reflectance Transformation Imaging (RTI)~\cite{giachetti2018} and Photometric Stereo~\cite{durou2020}, often require a precise understanding of the lighting conditions in the scene being captured. One common method for calibrating the lighting is to include one or more spheres in the scene, as shown in the left example of Figure~\ref{fig:intro}. However, manually outlining these spheres can be tedious and time-consuming, especially in the field of visual effects where the presence of chrome spheres is prevalent~\cite{jahirul_grey_2021}. This task can be made more efficient by using deep learning methods for detection. The goal of this project is to develop a neural network that can accurately detect both matte and shiny spheres in a scene.
\begin{figure}[h] \begin{figure}[ht]
\centering \centering
\begin{tabular}{cc} \begin{tabular}{cc}
\includegraphics[height=0.35\linewidth]{matte.jpg} & \includegraphics[height=0.35\linewidth]{matte.jpg} &
@ -44,7 +58,7 @@ The field of 3D reconstruction techniques in photography, such as Reflectance Tr
Previous work by Laurent Fainsin et al. in~\cite{spheredetect} attempted to address this problem by using a neural network called Mask R-CNN~\cite{MaskRCNN} for instance segmentation of spheres in images. However, this approach is limited in its ability to detect shiny spheres, as demonstrated in the right image of Figure~\ref{fig:previouswork}. The network was trained on images of matte spheres and was unable to generalize to shiny spheres, which highlights the need for further research in this area. Previous work by Laurent Fainsin et al. in~\cite{spheredetect} attempted to address this problem by using a neural network called Mask R-CNN~\cite{MaskRCNN} for instance segmentation of spheres in images. However, this approach is limited in its ability to detect shiny spheres, as demonstrated in the right image of Figure~\ref{fig:previouswork}. The network was trained on images of matte spheres and was unable to generalize to shiny spheres, which highlights the need for further research in this area.
\begin{figure}[h] \begin{figure}[ht]
\centering \centering
\begin{tabular}{cc} \begin{tabular}{cc}
\includegraphics[height=0.35\linewidth]{matte_inference.png} & \includegraphics[height=0.35\linewidth]{matte_inference.png} &
@ -54,39 +68,75 @@ Previous work by Laurent Fainsin et al. in~\cite{spheredetect} attempted to addr
\label{fig:previouswork} \label{fig:previouswork}
\end{figure} \end{figure}
\section{Current state of the art}
The automatic detection (or segmentation) of spheres in scenes is a rather niche task and as a result there exists no known direct method to solve this problem. The automatic detection (or segmentation) of spheres in scenes is a rather niche task and as a result there exists no known direct method to solve this problem.
\subsection{Datasets} \section{Datasets}
In~\cite{spheredetect}, it is explained that obtaining clean photographs with spherical markers for use in 3D reconstruction techniques are unsurprisingly rare. To address this issue, the authors of the paper crafted a training custom dataset using python and blender scripts. This was done by compositing known spherical markers (real or synthetic) onto background images from the COCO dataset~\cite{COCO}. The result of such technique is visible in Figure~\ref{fig:spheredetectdataset}. In~\cite{spheredetect}, it is explained that clean photographs with spherical markers for use in 3D reconstruction techniques are unsurprisingly rare. To address this issue, the authors of the paper crafted a training dataset using python and blender scripts. This was done by compositing known spherical markers (real or synthetic) onto background images from the COCO dataset~\cite{COCO}. The result of such technique is visible in Figure~\ref{fig:spheredetect_dataset}.
\begin{figure}[h] \begin{figure}[ht]
\centering \centering
\begin{tabular}{cc} \begin{tabular}{cc}
\includegraphics[height=0.3\linewidth]{dataset1.jpg} & \includegraphics[height=0.3\linewidth]{dataset1.jpg} &
\includegraphics[height=0.3\linewidth]{dataset2.jpg} \includegraphics[height=0.3\linewidth]{dataset2.jpg}
\end{tabular} \end{tabular}
\caption{Example of the synthetic dataset used in~\cite{spheredetect}.} \caption{Example of the synthetic dataset used in~\cite{spheredetect}.}
\label{fig:spheredetectdataset} \label{fig:spheredetect_dataset}
\end{figure} \end{figure}
During the research of this bibliography we found some additional datasets that we may be able to use. in the same way one you could generate synthetic images of chrome spheres using free (C0) env map from
\cite{legendre_deeplight_2019}
\cite{haven_hdris_nodate} \cite{haven_hdris_nodate}
\cite{murmann_dataset_2019}
\subsection{Models} \subsection{Antoine Laurent}
\subsubsection{Mask R-CNN} \begin{figure}[ht]
\centering
\begin{tabular}{cc}
\includegraphics[height=0.3\linewidth]{antoine_laurent_1.jpg} &
\includegraphics[height=0.3\linewidth]{antoine_laurent_2.jpg}
\end{tabular}
\caption{Example of clean photographs with spehrical markers from Antoine Laurent.}
\label{fig:antoine_laurent_dataset}
\end{figure}
\subsection{DeepLight}
\begin{figure}[ht]
\centering
\includegraphics[height=0.3\linewidth]{deeplight.png}
\caption{Example the dataset from~\cite{legendre_deeplight_2019}.}
\label{fig:deeplight_dataset}
\end{figure}
\subsection{Multi-Illumination Images in the Wild}
\begin{figure}[ht]
\centering
\begin{tabular}{cc}
\includegraphics[height=0.3\linewidth]{dir_7_mip2.jpg} &
\includegraphics[height=0.3\linewidth]{materials_mip2.png}
\end{tabular}
\caption{Example data from~\cite{murmann_dataset_2019}.}
\label{fig:murmann_dataset}
\end{figure}
\subsection{Labelling}
\cite{noauthor_label_nodate}
\subsection{Versionning}
\cite{noauthor_datasets_nodate}
\section{Models}
\subsection{Mask R-CNN}
In~\cite{spheredetect}, the authors use Mask R-CNN~\cite{MaskRCNN} as a base model for their task. Mask R-CNN is a neural network that is able to perform instance segmentation, which is the task of detecting and segmenting objects in an image. In~\cite{spheredetect}, the authors use Mask R-CNN~\cite{MaskRCNN} as a base model for their task. Mask R-CNN is a neural network that is able to perform instance segmentation, which is the task of detecting and segmenting objects in an image.
The network is composed of two parts: a backbone network and a region proposal network (RPN). The backbone network is a convolutional neural network that is used to extract features from the input image. The RPN is a fully convolutional network that is used to generate region proposals, which are bounding boxes that are used to crop the input image. The RPN is then used to generate a mask for each region proposal, which is used to segment the object in the image. The network is composed of two parts: a backbone network and a region proposal network (RPN). The backbone network is a convolutional neural network that is used to extract features from the input image. The RPN is a fully convolutional network that is used to generate region proposals, which are bounding boxes that are used to crop the input image. The RPN is then used to generate a mask for each region proposal, which is used to segment the object in the image.
\begin{figure}[h] \begin{figure}[ht]
\centering \centering
\includegraphics[width=0.6\linewidth]{MaskRCNN.png} \includegraphics[width=0.6\linewidth]{MaskRCNN.png}
\caption{The Mask-RCNN~\cite{MaskRCNN} architecture.} \caption{The Mask-RCNN~\cite{MaskRCNN} architecture.}
@ -97,31 +147,31 @@ The network is trained using a loss function that is composed of three terms: th
While the authors of the paper~\cite{spheredetect} obtain good results from this network on matte spheres, their performance drop when shiny spheres are introduced. This could be explained by the fact that convolutional neural network tend to extract local features from images. Indeed, you can only really indentify a chrome sphere if you can observe the "interior and exterior" of the sphere, delimited by a "distortion" effect. While the authors of the paper~\cite{spheredetect} obtain good results from this network on matte spheres, their performance drop when shiny spheres are introduced. This could be explained by the fact that convolutional neural network tend to extract local features from images. Indeed, you can only really indentify a chrome sphere if you can observe the "interior and exterior" of the sphere, delimited by a "distortion" effect.
\subsubsection{Ellipse R-CNN} \subsection{Ellipse R-CNN}
To detect spheres in images, it is sufficient to estimate the center and radius of their projected circles. However, due to the perspective nature of photographs, the circles are often distorted and appear as ellipses. To detect spheres in images, it is sufficient to estimate the center and radius of their projected circles. However, due to the perspective nature of photographs, the circles are often distorted and appear as ellipses.
The Ellipse R-CNN~\cite{dong_ellipse_2021} is a modified version of the Mask R-CNN~\cite{MaskRCNN} which can detect ellipses in images, it addresses this issue by using an additional branch in the network to predict the axes of the ellipse and its orientation, which allows for more accurate detection of objects and in our case spheres. It also have a feature of handling occlusion, by predicting the segmentation mask for each ellipse, it can handle overlapping and occluded objects. This makes it an ideal choice for detecting spheres in real-world images with complex backgrounds and variable lighting conditions. The Ellipse R-CNN~\cite{dong_ellipse_2021} is a modified version of the Mask R-CNN~\cite{MaskRCNN} which can detect ellipses in images, it addresses this issue by using an additional branch in the network to predict the axes of the ellipse and its orientation, which allows for more accurate detection of objects and in our case spheres. It also have a feature of handling occlusion, by predicting the segmentation mask for each ellipse, it can handle overlapping and occluded objects. This makes it an ideal choice for detecting spheres in real-world images with complex backgrounds and variable lighting conditions.
\begin{figure}[h] \begin{figure}[ht]
\centering \centering
\includegraphics[width=0.6\linewidth]{EllipseRCNN.png} \includegraphics[width=0.6\linewidth]{EllipseRCNN.png}
\caption{The Ellipse R-CNN~\cite{dong_ellipse_2021} architecture.} \caption{The Ellipse R-CNN~\cite{dong_ellipse_2021} architecture.}
\label{fig:ellipsercnn} \label{fig:ellipsercnn}
\end{figure} \end{figure}
\subsubsection{GPN} \subsection{GPN}
\begin{figure}[h] \begin{figure}[ht]
\centering \centering
\includegraphics[width=0.6\linewidth]{GPN.png} \includegraphics[width=0.6\linewidth]{GPN.png}
\caption{The GPN~\cite{li_detecting_2019} architecture.} \caption{The GPN~\cite{li_detecting_2019} architecture.}
\label{fig:gpn} \label{fig:gpn}
\end{figure} \end{figure}
\subsubsection{DETR} \subsection{DETR}
\begin{figure}[h] \begin{figure}[ht]
\centering \centering
\includegraphics[width=0.8\linewidth]{DETR.png} \includegraphics[width=0.8\linewidth]{DETR.png}
\caption{The DETR~\cite{carion_end--end_2020} architecture.} \caption{The DETR~\cite{carion_end--end_2020} architecture.}
@ -130,6 +180,16 @@ The Ellipse R-CNN~\cite{dong_ellipse_2021} is a modified version of the Mask R-C
+ \cite{zhang_dino_2022} + \cite{zhang_dino_2022}
\subsection{Mask2Former}
\section{Training}
\subsection{Loss functions}
\subsection{Metrics}
\subsection{Experiment tracking}
\section{Conclusion} \section{Conclusion}
From what we know it is now rather easy to elaborate a plan to try to solve our problem. ... From what we know it is now rather easy to elaborate a plan to try to solve our problem. ...
@ -137,6 +197,7 @@ From what we know it is now rather easy to elaborate a plan to try to solve our
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\newpage \newpage
\bibliography{zotero,qcav} \bibliography{zotero,qcav}
\bibliographystyle{plain} \bibliographystyle{plain}

14
src/paper.xmpdata Normal file
View file

@ -0,0 +1,14 @@
\Author{Laurent Fainsin}
\Title{
"Projet Long" Bibliography
}
\Language{English}
\Keywords{}
\Publisher{Self-Published}
\Subject{
Bibliography
}
\Date{2023-01-24}
\PublicationType{Bibliography}
\Source{}
\URLlink{}

View file

@ -9,7 +9,7 @@
author = {Van Strien, Daniel}, author = {Van Strien, Daniel},
month = aug, month = aug,
year = {2022}, year = {2022},
file = {Snapshot:/home/laurent/Zotero/storage/DXQJISMX/detr-object-detection.html:text/html} file = {Snapshot:/home/laurent/Zotero/storage/DXQJISMX/detr-object-detection.html:text/html},
} }
@article{dror_recognition_nodate, @article{dror_recognition_nodate,
@ -17,7 +17,7 @@
abstract = {This paper describes a machine vision system that classifies reflectance properties of surfaces such as metal, plastic, or paper, under unknown real-world illumination. We demonstrate performance of our algorithm for surfaces of arbitrary geometry. Reflectance estimation under arbitrary omnidirectional illumination proves highly underconstrained. Our reflectance estimation algorithm succeeds by learning relationships between surface reflectance and certain statistics computed from an observed image, which depend on statistical regularities in the spatial structure of real-world illumination. Although the algorithm assumes known geometry, its statistical nature makes it robust to inaccurate geometry estimates.}, abstract = {This paper describes a machine vision system that classifies reflectance properties of surfaces such as metal, plastic, or paper, under unknown real-world illumination. We demonstrate performance of our algorithm for surfaces of arbitrary geometry. Reflectance estimation under arbitrary omnidirectional illumination proves highly underconstrained. Our reflectance estimation algorithm succeeds by learning relationships between surface reflectance and certain statistics computed from an observed image, which depend on statistical regularities in the spatial structure of real-world illumination. Although the algorithm assumes known geometry, its statistical nature makes it robust to inaccurate geometry estimates.},
language = {en}, language = {en},
author = {Dror, Ron O and Adelson, Edward H and Willsky, Alan S}, author = {Dror, Ron O and Adelson, Edward H and Willsky, Alan S},
file = {Dror et al. - Recognition of Surface Reflectance Properties from .pdf:/home/laurent/Zotero/storage/HJXFDDT6/Dror et al. - Recognition of Surface Reflectance Properties from .pdf:application/pdf} file = {Dror et al. - Recognition of Surface Reflectance Properties from .pdf:/home/laurent/Zotero/storage/HJXFDDT6/Dror et al. - Recognition of Surface Reflectance Properties from .pdf:application/pdf},
} }
@article{legendre_deeplight_2019, @article{legendre_deeplight_2019,
@ -26,7 +26,7 @@
language = {en}, language = {en},
author = {LeGendre, Chloe and Ma, Wan-Chun and Fyffe, Graham and Flynn, John and Charbonnel, Laurent and Busch, Jay and Debevec, Paul}, author = {LeGendre, Chloe and Ma, Wan-Chun and Fyffe, Graham and Flynn, John and Charbonnel, Laurent and Busch, Jay and Debevec, Paul},
year = {2019}, year = {2019},
file = {LeGendre et al. - DeepLight Learning Illumination for Unconstrained.pdf:/home/laurent/Zotero/storage/7FGL25G5/LeGendre et al. - DeepLight Learning Illumination for Unconstrained.pdf:application/pdf} file = {LeGendre et al. - DeepLight Learning Illumination for Unconstrained.pdf:/home/laurent/Zotero/storage/7FGL25G5/LeGendre et al. - DeepLight Learning Illumination for Unconstrained.pdf:application/pdf},
} }
@misc{tazi_fine-tuning_nodate, @misc{tazi_fine-tuning_nodate,
@ -36,7 +36,7 @@
language = {en}, language = {en},
urldate = {2023-01-17}, urldate = {2023-01-17},
author = {Tazi, Nouamane}, author = {Tazi, Nouamane},
file = {Snapshot:/home/laurent/Zotero/storage/WHFVB3QC/fine-tuning-detr-for-license-plates-detection.html:text/html} file = {Snapshot:/home/laurent/Zotero/storage/WHFVB3QC/fine-tuning-detr-for-license-plates-detection.html:text/html},
} }
@inproceedings{murmann_dataset_2019, @inproceedings{murmann_dataset_2019,
@ -54,7 +54,7 @@
month = oct, month = oct,
year = {2019}, year = {2019},
pages = {4079--4088}, pages = {4079--4088},
file = {Murmann et al. - 2019 - A Dataset of Multi-Illumination Images in the Wild.pdf:/home/laurent/Zotero/storage/KH9HA9SQ/Murmann et al. - 2019 - A Dataset of Multi-Illumination Images in the Wild.pdf:application/pdf} file = {Murmann et al. - 2019 - A Dataset of Multi-Illumination Images in the Wild.pdf:/home/laurent/Zotero/storage/KH9HA9SQ/Murmann et al. - 2019 - A Dataset of Multi-Illumination Images in the Wild.pdf:application/pdf},
} }
@misc{arora_annotated_2021, @misc{arora_annotated_2021,
@ -67,7 +67,7 @@
author = {Arora, Aman}, author = {Arora, Aman},
month = jul, month = jul,
year = {2021}, year = {2021},
file = {Snapshot:/home/laurent/Zotero/storage/G78PSBHE/annotateddetr.html:text/html} file = {Snapshot:/home/laurent/Zotero/storage/G78PSBHE/annotateddetr.html:text/html},
} }
@misc{carion_end--end_2020, @misc{carion_end--end_2020,
@ -82,7 +82,7 @@
year = {2020}, year = {2020},
note = {arXiv:2005.12872 [cs]}, note = {arXiv:2005.12872 [cs]},
keywords = {Computer Science - Computer Vision and Pattern Recognition}, keywords = {Computer Science - Computer Vision and Pattern Recognition},
file = {arXiv Fulltext PDF:/home/laurent/Zotero/storage/KBRPD4CU/Carion et al. - 2020 - End-to-End Object Detection with Transformers.pdf:application/pdf;arXiv.org Snapshot:/home/laurent/Zotero/storage/6445LQV5/2005.html:text/html} file = {arXiv Fulltext PDF:/home/laurent/Zotero/storage/KBRPD4CU/Carion et al. - 2020 - End-to-End Object Detection with Transformers.pdf:application/pdf;arXiv.org Snapshot:/home/laurent/Zotero/storage/6445LQV5/2005.html:text/html},
} }
@misc{li_detecting_2019, @misc{li_detecting_2019,
@ -97,7 +97,7 @@
year = {2019}, year = {2019},
note = {arXiv:1902.09658 [cs]}, note = {arXiv:1902.09658 [cs]},
keywords = {Computer Science - Computer Vision and Pattern Recognition}, keywords = {Computer Science - Computer Vision and Pattern Recognition},
file = {arXiv Fulltext PDF:/home/laurent/Zotero/storage/IB8AWGHV/Li - 2019 - Detecting Lesion Bounding Ellipses With Gaussian P.pdf:application/pdf;arXiv.org Snapshot:/home/laurent/Zotero/storage/ZGKBBB98/1902.html:text/html} file = {arXiv Fulltext PDF:/home/laurent/Zotero/storage/IB8AWGHV/Li - 2019 - Detecting Lesion Bounding Ellipses With Gaussian P.pdf:application/pdf;arXiv.org Snapshot:/home/laurent/Zotero/storage/ZGKBBB98/1902.html:text/html},
} }
@misc{noauthor_detr_nodate, @misc{noauthor_detr_nodate,
@ -105,14 +105,14 @@
url = {https://huggingface.co/docs/transformers/model_doc/detr}, url = {https://huggingface.co/docs/transformers/model_doc/detr},
abstract = {Were on a journey to advance and democratize artificial intelligence through open source and open science.}, abstract = {Were on a journey to advance and democratize artificial intelligence through open source and open science.},
urldate = {2023-01-17}, urldate = {2023-01-17},
file = {Snapshot:/home/laurent/Zotero/storage/2AQYDSL3/detr.html:text/html} file = {Snapshot:/home/laurent/Zotero/storage/2AQYDSL3/detr.html:text/html},
} }
@misc{noauthor_opencv_nodate, @misc{noauthor_opencv_nodate,
title = {{OpenCV}: {Camera} {Calibration}}, title = {{OpenCV}: {Camera} {Calibration}},
url = {https://docs.opencv.org/4.x/dc/dbb/tutorial_py_calibration.html}, url = {https://docs.opencv.org/4.x/dc/dbb/tutorial_py_calibration.html},
urldate = {2023-01-17}, urldate = {2023-01-17},
file = {OpenCV\: Camera Calibration:/home/laurent/Zotero/storage/7C3DT2WU/tutorial_py_calibration.html:text/html} file = {OpenCV\: Camera Calibration:/home/laurent/Zotero/storage/7C3DT2WU/tutorial_py_calibration.html:text/html},
} }
@misc{jahirul_grey_2021, @misc{jahirul_grey_2021,
@ -123,7 +123,7 @@
author = {Jahirul, Amin}, author = {Jahirul, Amin},
month = jul, month = jul,
year = {2021}, year = {2021},
file = {Snapshot:/home/laurent/Zotero/storage/TM2TJKMH/the-grey-the-chrome-and-the-macbeth-chart.html:text/html} file = {Snapshot:/home/laurent/Zotero/storage/TM2TJKMH/the-grey-the-chrome-and-the-macbeth-chart.html:text/html},
} }
@misc{doppenberg_lunar_2022, @misc{doppenberg_lunar_2022,
@ -136,7 +136,7 @@
month = aug, month = aug,
year = {2022}, year = {2022},
note = {original-date: 2020-10-19T16:32:29Z}, note = {original-date: 2020-10-19T16:32:29Z},
keywords = {crater-detection, ellipse-rcnn, faster-rcnn, space-engineering} keywords = {crater-detection, ellipse-rcnn, faster-rcnn, space-engineering},
} }
@misc{doppenberg_ellipse_2022, @misc{doppenberg_ellipse_2022,
@ -149,7 +149,7 @@
month = dec, month = dec,
year = {2022}, year = {2022},
note = {original-date: 2021-06-25T09:21:44Z}, note = {original-date: 2021-06-25T09:21:44Z},
keywords = {ellipse-rcnn, deep-learning, pytorch, pytorch-lightning, region-based} keywords = {ellipse-rcnn, deep-learning, pytorch, pytorch-lightning, region-based},
} }
@misc{wok_finetune_2022, @misc{wok_finetune_2022,
@ -162,7 +162,7 @@
month = dec, month = dec,
year = {2022}, year = {2022},
note = {original-date: 2020-08-03T17:17:35Z}, note = {original-date: 2020-08-03T17:17:35Z},
keywords = {balloon, balloons, colab, colab-notebook, colaboratory, detr, facebook, finetune, finetunes, finetuning, google-colab, google-colab-notebook, google-colaboratory, instance, instance-segmentation, instances, segementation, segment} keywords = {balloon, balloons, colab, colab-notebook, colaboratory, detr, facebook, finetune, finetunes, finetuning, google-colab, google-colab-notebook, google-colaboratory, instance, instance-segmentation, instances, segementation, segment},
} }
@misc{noauthor_datasets_nodate, @misc{noauthor_datasets_nodate,
@ -170,7 +170,7 @@
url = {https://huggingface.co/docs/datasets/index}, url = {https://huggingface.co/docs/datasets/index},
abstract = {Were on a journey to advance and democratize artificial intelligence through open source and open science.}, abstract = {Were on a journey to advance and democratize artificial intelligence through open source and open science.},
urldate = {2023-01-17}, urldate = {2023-01-17},
file = {Snapshot:/home/laurent/Zotero/storage/RYXSCZR7/index.html:text/html} file = {Snapshot:/home/laurent/Zotero/storage/RYXSCZR7/index.html:text/html},
} }
@misc{rogge_transformers_2020, @misc{rogge_transformers_2020,
@ -182,7 +182,7 @@
author = {Rogge, Niels}, author = {Rogge, Niels},
month = sep, month = sep,
year = {2020}, year = {2020},
doi = {10.5281/zenodo.1234} doi = {10.5281/zenodo.1234},
} }
@misc{noauthor_recommendations_2020, @misc{noauthor_recommendations_2020,
@ -195,14 +195,14 @@
journal = {GitHub}, journal = {GitHub},
month = may, month = may,
year = {2020}, year = {2020},
file = {Snapshot:/home/laurent/Zotero/storage/G2S6584X/9.html:text/html} file = {Snapshot:/home/laurent/Zotero/storage/G2S6584X/9.html:text/html},
} }
@misc{noauthor_auto_nodate, @misc{noauthor_auto_nodate,
title = {Auto {Classes}}, title = {Auto {Classes}},
url = {https://huggingface.co/docs/transformers/model_doc/auto}, url = {https://huggingface.co/docs/transformers/model_doc/auto},
abstract = {Were on a journey to advance and democratize artificial intelligence through open source and open science.}, abstract = {Were on a journey to advance and democratize artificial intelligence through open source and open science.},
urldate = {2023-01-17} urldate = {2023-01-17},
} }
@misc{noauthor_swin_nodate, @misc{noauthor_swin_nodate,
@ -210,7 +210,7 @@
url = {https://huggingface.co/docs/transformers/v4.24.0/en/model_doc/swin}, url = {https://huggingface.co/docs/transformers/v4.24.0/en/model_doc/swin},
abstract = {Were on a journey to advance and democratize artificial intelligence through open source and open science.}, abstract = {Were on a journey to advance and democratize artificial intelligence through open source and open science.},
urldate = {2023-01-17}, urldate = {2023-01-17},
file = {Snapshot:/home/laurent/Zotero/storage/K2NDEY49/swin.html:text/html} file = {Snapshot:/home/laurent/Zotero/storage/K2NDEY49/swin.html:text/html},
} }
@misc{rajesh_pytorch_2022, @misc{rajesh_pytorch_2022,
@ -222,7 +222,7 @@
month = sep, month = sep,
year = {2022}, year = {2022},
note = {original-date: 2021-05-02T03:32:10Z}, note = {original-date: 2021-05-02T03:32:10Z},
keywords = {deep-learning, pytorch, deep-learning-algorithms, pytorch-implementation, transformer-architecture} keywords = {deep-learning, pytorch, deep-learning-algorithms, pytorch-implementation, transformer-architecture},
} }
@misc{mmdetection_contributors_openmmlab_2018, @misc{mmdetection_contributors_openmmlab_2018,
@ -234,7 +234,7 @@
author = {{MMDetection Contributors}}, author = {{MMDetection Contributors}},
month = aug, month = aug,
year = {2018}, year = {2018},
note = {original-date: 2018-08-22T07:06:06Z} note = {original-date: 2018-08-22T07:06:06Z},
} }
@misc{noauthor_awesome_2023, @misc{noauthor_awesome_2023,
@ -245,7 +245,7 @@
publisher = {IDEA-Research}, publisher = {IDEA-Research},
month = jan, month = jan,
year = {2023}, year = {2023},
note = {original-date: 2022-03-09T05:11:49Z} note = {original-date: 2022-03-09T05:11:49Z},
} }
@misc{arakelyan_aim_2020, @misc{arakelyan_aim_2020,
@ -257,24 +257,24 @@
author = {Arakelyan, Gor and Soghomonyan, Gevorg and {The Aim team}}, author = {Arakelyan, Gor and Soghomonyan, Gevorg and {The Aim team}},
month = jun, month = jun,
year = {2020}, year = {2020},
doi = {10.5281/zenodo.6536395} doi = {10.5281/zenodo.6536395},
} }
@misc{noauthor_open_nodate, @misc{noauthor_label_nodate,
title = {Open {Source} {Data} {Labeling}}, title = {Label {Studio}},
url = {https://labelstud.io/}, url = {https://labelstud.io/},
abstract = {A flexible data labeling tool for all data types. Prepare training data for computer vision, natural language processing, speech, voice, and video models.}, abstract = {A flexible data labeling tool for all data types. Prepare training data for computer vision, natural language processing, speech, voice, and video models.},
language = {en}, language = {en},
urldate = {2023-01-17}, urldate = {2023-01-17},
journal = {Label Studio}, journal = {Label Studio},
file = {Snapshot:/home/laurent/Zotero/storage/7Y3X7GTY/labelstud.io.html:text/html} file = {Snapshot:/home/laurent/Zotero/storage/7Y3X7GTY/labelstud.io.html:text/html},
} }
@misc{noauthor_miscellaneous_nodate, @misc{noauthor_miscellaneous_nodate,
title = {Miscellaneous {Transformations} and {Projections}}, title = {Miscellaneous {Transformations} and {Projections}},
url = {http://paulbourke.net/geometry/transformationprojection/}, url = {http://paulbourke.net/geometry/transformationprojection/},
urldate = {2023-01-17}, urldate = {2023-01-17},
file = {Miscellaneous Transformations and Projections:/home/laurent/Zotero/storage/WP7ZDCKF/transformationprojection.html:text/html} file = {Miscellaneous Transformations and Projections:/home/laurent/Zotero/storage/WP7ZDCKF/transformationprojection.html:text/html},
} }
@article{jun-fang_wu_nonmetric_2010, @article{jun-fang_wu_nonmetric_2010,
@ -292,7 +292,7 @@
Place: Wuhan, China Place: Wuhan, China
Publisher: IEEE}, Publisher: IEEE},
pages = {3338--3341}, pages = {3338--3341},
annote = {[TLDR] The proposed approach is entirely noniterative, therefore it keeps away from the procedure of iterative optimization and is nonmetric, thus it is low cost and the capability of the method to resist noise is satisfying.} annote = {[TLDR] The proposed approach is entirely noniterative, therefore it keeps away from the procedure of iterative optimization and is nonmetric, thus it is low cost and the capability of the method to resist noise is satisfying.},
} }
@misc{qiu_describing_2021, @misc{qiu_describing_2021,
@ -308,7 +308,7 @@
note = {arXiv:2103.14146 [cs]}, note = {arXiv:2103.14146 [cs]},
keywords = {Computer Science - Computer Vision and Pattern Recognition}, keywords = {Computer Science - Computer Vision and Pattern Recognition},
annote = {Comment: Accepted by ICCV2021. 18 pages, 15 figures, project page: https://cvpaperchallenge.github.io/Describing-and-Localizing-Multiple-Change-with-Transformers/}, annote = {Comment: Accepted by ICCV2021. 18 pages, 15 figures, project page: https://cvpaperchallenge.github.io/Describing-and-Localizing-Multiple-Change-with-Transformers/},
file = {arXiv Fulltext PDF:/home/laurent/Zotero/storage/6GLDC5C7/Qiu et al. - 2021 - Describing and Localizing Multiple Changes with Tr.pdf:application/pdf;arXiv.org Snapshot:/home/laurent/Zotero/storage/4ZUPCEKT/2103.html:text/html} file = {arXiv Fulltext PDF:/home/laurent/Zotero/storage/6GLDC5C7/Qiu et al. - 2021 - Describing and Localizing Multiple Changes with Tr.pdf:application/pdf;arXiv.org Snapshot:/home/laurent/Zotero/storage/4ZUPCEKT/2103.html:text/html},
} }
@misc{lahoud_3d_2022, @misc{lahoud_3d_2022,
@ -324,7 +324,7 @@
year = {2022}, year = {2022},
note = {arXiv:2208.04309 [cs]}, note = {arXiv:2208.04309 [cs]},
keywords = {Computer Science - Computer Vision and Pattern Recognition}, keywords = {Computer Science - Computer Vision and Pattern Recognition},
file = {arXiv Fulltext PDF:/home/laurent/Zotero/storage/AN3SNSVC/Lahoud et al. - 2022 - 3D Vision with Transformers A Survey.pdf:application/pdf;arXiv.org Snapshot:/home/laurent/Zotero/storage/6BXWCFI5/2208.html:text/html} file = {arXiv Fulltext PDF:/home/laurent/Zotero/storage/AN3SNSVC/Lahoud et al. - 2022 - 3D Vision with Transformers A Survey.pdf:application/pdf;arXiv.org Snapshot:/home/laurent/Zotero/storage/6BXWCFI5/2208.html:text/html},
} }
@misc{noauthor_weights_nodate, @misc{noauthor_weights_nodate,
@ -332,7 +332,7 @@
url = {https://wandb.ai/site/, http://wandb.ai/site}, url = {https://wandb.ai/site/, http://wandb.ai/site},
abstract = {WandB is a central dashboard to keep track of your hyperparameters, system metrics, and predictions so you can compare models live, and share your findings.}, abstract = {WandB is a central dashboard to keep track of your hyperparameters, system metrics, and predictions so you can compare models live, and share your findings.},
urldate = {2023-01-17}, urldate = {2023-01-17},
file = {Snapshot:/home/laurent/Zotero/storage/GRIMYX6J/site.html:text/html} file = {Snapshot:/home/laurent/Zotero/storage/GRIMYX6J/site.html:text/html},
} }
@article{dong_ellipse_2021, @article{dong_ellipse_2021,
@ -351,7 +351,7 @@
keywords = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Robotics}, keywords = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Robotics},
pages = {2193--2206}, pages = {2193--2206},
annote = {Comment: 18 pages, 20 figures, 7 tables}, annote = {Comment: 18 pages, 20 figures, 7 tables},
file = {arXiv Fulltext PDF:/home/laurent/Zotero/storage/QERXUH24/Dong et al. - 2021 - Ellipse R-CNN Learning to Infer Elliptical Object.pdf:application/pdf;arXiv.org Snapshot:/home/laurent/Zotero/storage/KNUA7S3S/2001.html:text/html} file = {arXiv Fulltext PDF:/home/laurent/Zotero/storage/QERXUH24/Dong et al. - 2021 - Ellipse R-CNN Learning to Infer Elliptical Object.pdf:application/pdf;arXiv.org Snapshot:/home/laurent/Zotero/storage/KNUA7S3S/2001.html:text/html},
} }
@misc{haven_hdris_nodate, @misc{haven_hdris_nodate,
@ -361,7 +361,7 @@
language = {en}, language = {en},
urldate = {2023-01-17}, urldate = {2023-01-17},
journal = {Poly Haven}, journal = {Poly Haven},
author = {Haven, Poly} author = {Haven, Poly},
} }
@misc{zhang_dino_2022, @misc{zhang_dino_2022,
@ -377,5 +377,5 @@
year = {2022}, year = {2022},
note = {arXiv:2203.03605 [cs]}, note = {arXiv:2203.03605 [cs]},
keywords = {Computer Science - Computer Vision and Pattern Recognition}, keywords = {Computer Science - Computer Vision and Pattern Recognition},
file = {arXiv Fulltext PDF:/home/laurent/Zotero/storage/NFL7ASJI/Zhang et al. - 2022 - DINO DETR with Improved DeNoising Anchor Boxes fo.pdf:application/pdf;arXiv.org Snapshot:/home/laurent/Zotero/storage/IJEI9W7E/2203.html:text/html} file = {arXiv Fulltext PDF:/home/laurent/Zotero/storage/NFL7ASJI/Zhang et al. - 2022 - DINO DETR with Improved DeNoising Anchor Boxes fo.pdf:application/pdf;arXiv.org Snapshot:/home/laurent/Zotero/storage/IJEI9W7E/2203.html:text/html},
} }