Zobrazeno 1 - 10
of 126
pro vyhledávání: '"AUBRY, MATHIEU"'
We introduce a general detection-based approach to text line recognition, be it printed (OCR) or handwritten (HTR), with Latin, Chinese, or ciphered characters. Detection-based approaches have until now been largely discarded for HTR because reading
Externí odkaz:
http://arxiv.org/abs/2409.17095
Autor:
Vincent, Elliot, Saroufim, Mehraïl, Chemla, Jonathan, Ubelmann, Yves, Marquis, Philippe, Ponce, Jean, Aubry, Mathieu
Archaeological sites are the physical remains of past human activity and one of the main sources of information about past societies and cultures. However, they are also the target of malevolent human actions, especially in countries having experienc
Externí odkaz:
http://arxiv.org/abs/2409.09432
Defining script types and establishing classification criteria for medieval handwriting is a central aspect of palaeographical analysis. However, existing typologies often encounter methodological challenges, such as descriptive limitations and subje
Externí odkaz:
http://arxiv.org/abs/2408.11150
Autor:
Chaki, Sayan Kumar, Baltaci, Zeynep Sonat, Vincent, Elliot, Emonet, Remi, Vial-Bonacci, Fabienne, Bahier-Porte, Christelle, Aubry, Mathieu, Fournel, Thierry
This paper aims to develop the study of historical printed ornaments with modern unsupervised computer vision. We highlight three complex tasks that are of critical interest to book historians: clustering, element discovery, and unsupervised change l
Externí odkaz:
http://arxiv.org/abs/2408.08633
This paper demonstrates how to use generative models trained for image synthesis as tools for visual data mining. Our insight is that since contemporary generative models learn an accurate representation of their training data, we can use them to sum
Externí odkaz:
http://arxiv.org/abs/2408.02752
Satellite imagery plays a crucial role in monitoring changes happening on Earth's surface and aiding in climate analysis, ecosystem assessment, and disaster response. In this paper, we tackle semantic change detection with satellite image time series
Externí odkaz:
http://arxiv.org/abs/2407.07616
Automatically extracting the geometric content from the hundreds of thousands of diagrams drawn in historical manuscripts would enable historians to study the diffusion of astronomical knowledge on a global scale. However, state-of-the-art vectorizat
Externí odkaz:
http://arxiv.org/abs/2403.08721
Autor:
Cífka, Martin, Ponimatkin, Georgy, Labbé, Yann, Russell, Bryan, Aubry, Mathieu, Petrik, Vladimir, Sivic, Josef
We introduce FocalPose++, a neural render-and-compare method for jointly estimating the camera-object 6D pose and camera focal length given a single RGB input image depicting a known object. The contributions of this work are threefold. First, we der
Externí odkaz:
http://arxiv.org/abs/2312.02985
Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. While many approaches focus on recovering high-fidelity 3D scenes, we focus on pars
Externí odkaz:
http://arxiv.org/abs/2307.05473
We propose an unsupervised method for parsing large 3D scans of real-world scenes with easily-interpretable shapes. This work aims to provide a practical tool for analyzing 3D scenes in the context of aerial surveying and mapping, without the need fo
Externí odkaz:
http://arxiv.org/abs/2304.09704