Nicolas Gonthier
@nicaogr.bsky.social
PhD - R&D Engineer at French Mapping Agency @ignfrance.bsky.social working on Deep Learning and computer Vision for Earth observation
Pinned
Nicolas Gonthier
@nicaogr.bsky.social
· Oct 15
New version of the MAESTRO paper about self-supervised Learning for Earth Observation Data 🛰️✈️🗺️
arxiv.org/abs/2508.10894
We provide an intense benchmark of different ways to deal with multitemporal, multispectral, and multimodal data (fusion strategies / normalization schemes) for MAE based model.
arxiv.org/abs/2508.10894
We provide an intense benchmark of different ways to deal with multitemporal, multispectral, and multimodal data (fusion strategies / normalization schemes) for MAE based model.
New version of the MAESTRO paper about self-supervised Learning for Earth Observation Data 🛰️✈️🗺️
arxiv.org/abs/2508.10894
We provide an intense benchmark of different ways to deal with multitemporal, multispectral, and multimodal data (fusion strategies / normalization schemes) for MAE based model.
arxiv.org/abs/2508.10894
We provide an intense benchmark of different ways to deal with multitemporal, multispectral, and multimodal data (fusion strategies / normalization schemes) for MAE based model.
November 12, 2025 at 8:28 AM
The new version of my preprint review on Operational Change Detection for Geographical Information is now available on ArXiv : arxiv.org/abs/2503.14109
This review contains insights about the current problems to scale up change detection for geospatial databases used by National Mapping Agencies.
This review contains insights about the current problems to scale up change detection for geospatial databases used by National Mapping Agencies.
Operational Change Detection for Geographical Information: Overview and Challenges
Rapid evolution of territories due to climate change and human impact requires prompt and effective updates to geospatial databases maintained by the National Mapping Agency. This paper presents a com...
arxiv.org
November 3, 2025 at 5:30 PM
The new version of my preprint review on Operational Change Detection for Geographical Information is now available on ArXiv : arxiv.org/abs/2503.14109
This review contains insights about the current problems to scale up change detection for geospatial databases used by National Mapping Agencies.
This review contains insights about the current problems to scale up change detection for geospatial databases used by National Mapping Agencies.
Reposted by Nicolas Gonthier
📢 FLAIR-HUB dataset
A new large-scale, multimodal dataset for land cover and crop type mapping
🤗 Dataset: huggingface.co/datasets/IGN...
📄 Preprint: arxiv.org/abs/2506.07080
🤗 Pretrained models: huggingface.co/collections/...
💻 Code: github.com/IGNF/FLAIR-HUB
🌐 Project : arxiv.org/abs/2506.07080
A new large-scale, multimodal dataset for land cover and crop type mapping
🤗 Dataset: huggingface.co/datasets/IGN...
📄 Preprint: arxiv.org/abs/2506.07080
🤗 Pretrained models: huggingface.co/collections/...
💻 Code: github.com/IGNF/FLAIR-HUB
🌐 Project : arxiv.org/abs/2506.07080
FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping
The growing availability of high-quality Earth Observation (EO) data enables accurate global land cover and crop type monitoring. However, the volume and heterogeneity of these datasets pose major pro...
arxiv.org
June 11, 2025 at 2:00 PM
📢 FLAIR-HUB dataset
A new large-scale, multimodal dataset for land cover and crop type mapping
🤗 Dataset: huggingface.co/datasets/IGN...
📄 Preprint: arxiv.org/abs/2506.07080
🤗 Pretrained models: huggingface.co/collections/...
💻 Code: github.com/IGNF/FLAIR-HUB
🌐 Project : arxiv.org/abs/2506.07080
A new large-scale, multimodal dataset for land cover and crop type mapping
🤗 Dataset: huggingface.co/datasets/IGN...
📄 Preprint: arxiv.org/abs/2506.07080
🤗 Pretrained models: huggingface.co/collections/...
💻 Code: github.com/IGNF/FLAIR-HUB
🌐 Project : arxiv.org/abs/2506.07080
New version of the MAESTRO paper about self-supervised Learning for Earth Observation Data 🛰️✈️🗺️
arxiv.org/abs/2508.10894
We provide an intense benchmark of different ways to deal with multitemporal, multispectral, and multimodal data (fusion strategies / normalization schemes) for MAE based model.
arxiv.org/abs/2508.10894
We provide an intense benchmark of different ways to deal with multitemporal, multispectral, and multimodal data (fusion strategies / normalization schemes) for MAE based model.
October 15, 2025 at 10:29 AM
New version of the MAESTRO paper about self-supervised Learning for Earth Observation Data 🛰️✈️🗺️
arxiv.org/abs/2508.10894
We provide an intense benchmark of different ways to deal with multitemporal, multispectral, and multimodal data (fusion strategies / normalization schemes) for MAE based model.
arxiv.org/abs/2508.10894
We provide an intense benchmark of different ways to deal with multitemporal, multispectral, and multimodal data (fusion strategies / normalization schemes) for MAE based model.
Reposted by Nicolas Gonthier
💶 Shape the future look of the euro!
The European Central Bank has launched a design contest for new euro banknotes with two themes:
🖼️ European Culture
🐦 R️ivers & Birds
Open to designers across the EU, submit your ideas by 18 August 12:00 CET
→ europa.eu/!cWfmdT
The European Central Bank has launched a design contest for new euro banknotes with two themes:
🖼️ European Culture
🐦 R️ivers & Birds
Open to designers across the EU, submit your ideas by 18 August 12:00 CET
→ europa.eu/!cWfmdT
August 6, 2025 at 7:03 AM
💶 Shape the future look of the euro!
The European Central Bank has launched a design contest for new euro banknotes with two themes:
🖼️ European Culture
🐦 R️ivers & Birds
Open to designers across the EU, submit your ideas by 18 August 12:00 CET
→ europa.eu/!cWfmdT
The European Central Bank has launched a design contest for new euro banknotes with two themes:
🖼️ European Culture
🐦 R️ivers & Birds
Open to designers across the EU, submit your ideas by 18 August 12:00 CET
→ europa.eu/!cWfmdT
Reposted by Nicolas Gonthier
Reposted by Nicolas Gonthier
Anatol Garioud, S\'ebastien Giordano, Nicolas David, Nicolas Gonthier
FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping
https://arxiv.org/abs/2506.07080
FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping
https://arxiv.org/abs/2506.07080
June 10, 2025 at 1:17 PM
Anatol Garioud, S\'ebastien Giordano, Nicolas David, Nicolas Gonthier
FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping
https://arxiv.org/abs/2506.07080
FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping
https://arxiv.org/abs/2506.07080
Reposted by Nicolas Gonthier
🛰️ At #CVPR2025 presenting "AnySat: An Earth Observation Model for Any Resolutions, Scales, and Modalities" - Saturday afternoon, Poster 355!
If you're here and want to discuss geolocation or geospatial foundation models, let's connect!
If you're here and want to discuss geolocation or geospatial foundation models, let's connect!
June 11, 2025 at 9:08 PM
🛰️ At #CVPR2025 presenting "AnySat: An Earth Observation Model for Any Resolutions, Scales, and Modalities" - Saturday afternoon, Poster 355!
If you're here and want to discuss geolocation or geospatial foundation models, let's connect!
If you're here and want to discuss geolocation or geospatial foundation models, let's connect!
I wil𝗹𝗹 𝗽𝗿𝗲𝘀𝗲𝗻𝘁: HySCDG, a generative pipeline for creating a large hybrid semantic change detection for Earth Observation
🖼️ 𝗣𝗼𝘀𝘁𝗲𝗿 #187 Session 1,
This Friday, June 13 10:30 - 12:30 #CVPR2025
📄 Paper: arxiv.org/abs/2503.15683
🔗 Project: yb23.github.io/projects/cywd/
🖼️ 𝗣𝗼𝘀𝘁𝗲𝗿 #187 Session 1,
This Friday, June 13 10:30 - 12:30 #CVPR2025
📄 Paper: arxiv.org/abs/2503.15683
🔗 Project: yb23.github.io/projects/cywd/
June 11, 2025 at 9:03 PM
I wil𝗹𝗹 𝗽𝗿𝗲𝘀𝗲𝗻𝘁: HySCDG, a generative pipeline for creating a large hybrid semantic change detection for Earth Observation
🖼️ 𝗣𝗼𝘀𝘁𝗲𝗿 #187 Session 1,
This Friday, June 13 10:30 - 12:30 #CVPR2025
📄 Paper: arxiv.org/abs/2503.15683
🔗 Project: yb23.github.io/projects/cywd/
🖼️ 𝗣𝗼𝘀𝘁𝗲𝗿 #187 Session 1,
This Friday, June 13 10:30 - 12:30 #CVPR2025
📄 Paper: arxiv.org/abs/2503.15683
🔗 Project: yb23.github.io/projects/cywd/
I am at #CVPR2025 this week, don't hesitate to reach me if you want to talk about remote sensing, change detection, multimodal self supervised learning, generative modeling for synthetic dataset and earth observation.
June 11, 2025 at 3:22 PM
I am at #CVPR2025 this week, don't hesitate to reach me if you want to talk about remote sensing, change detection, multimodal self supervised learning, generative modeling for synthetic dataset and earth observation.
I am at #CVPR2025 this week, don't hesitate to reach me if you want to talk about remote sensing, change detection, multimodal self supervised learning, generative modeling for synthetic dataset and earth observation.
June 11, 2025 at 3:03 PM
I am at #CVPR2025 this week, don't hesitate to reach me if you want to talk about remote sensing, change detection, multimodal self supervised learning, generative modeling for synthetic dataset and earth observation.
📢 FLAIR-HUB dataset
A new large-scale, multimodal dataset for land cover and crop type mapping
🤗 Dataset: huggingface.co/datasets/IGN...
📄 Preprint: arxiv.org/abs/2506.07080
🤗 Pretrained models: huggingface.co/collections/...
💻 Code: github.com/IGNF/FLAIR-HUB
🌐 Project : arxiv.org/abs/2506.07080
A new large-scale, multimodal dataset for land cover and crop type mapping
🤗 Dataset: huggingface.co/datasets/IGN...
📄 Preprint: arxiv.org/abs/2506.07080
🤗 Pretrained models: huggingface.co/collections/...
💻 Code: github.com/IGNF/FLAIR-HUB
🌐 Project : arxiv.org/abs/2506.07080
FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping
The growing availability of high-quality Earth Observation (EO) data enables accurate global land cover and crop type monitoring. However, the volume and heterogeneity of these datasets pose major pro...
arxiv.org
June 11, 2025 at 2:00 PM
📢 FLAIR-HUB dataset
A new large-scale, multimodal dataset for land cover and crop type mapping
🤗 Dataset: huggingface.co/datasets/IGN...
📄 Preprint: arxiv.org/abs/2506.07080
🤗 Pretrained models: huggingface.co/collections/...
💻 Code: github.com/IGNF/FLAIR-HUB
🌐 Project : arxiv.org/abs/2506.07080
A new large-scale, multimodal dataset for land cover and crop type mapping
🤗 Dataset: huggingface.co/datasets/IGN...
📄 Preprint: arxiv.org/abs/2506.07080
🤗 Pretrained models: huggingface.co/collections/...
💻 Code: github.com/IGNF/FLAIR-HUB
🌐 Project : arxiv.org/abs/2506.07080
Reposted by Nicolas Gonthier
This is my PhD thesis
I did not ask for this
I did not consent to this
I did not approve of this
I was not compensated for this
I would not have advised this
I do not like this
And worst of all, the number of people who've read my thesis has still not increased.
I did not ask for this
I did not consent to this
I did not approve of this
I was not compensated for this
I would not have advised this
I do not like this
And worst of all, the number of people who've read my thesis has still not increased.
June 2, 2025 at 8:03 PM
This is my PhD thesis
I did not ask for this
I did not consent to this
I did not approve of this
I was not compensated for this
I would not have advised this
I do not like this
And worst of all, the number of people who've read my thesis has still not increased.
I did not ask for this
I did not consent to this
I did not approve of this
I was not compensated for this
I would not have advised this
I do not like this
And worst of all, the number of people who've read my thesis has still not increased.
Reposted by Nicolas Gonthier
Quand on alertait sur le fait que Academia était un acteur privé, lucratif, parasite pour la recherche publique, qui commercialisait les données, on nous répondait souvent "oui, mais c'est carrément mieux que HAL par exemple, qui n'est pas intuitif".
Voilà le résultat...
Voilà le résultat...
This is my PhD thesis
I did not ask for this
I did not consent to this
I did not approve of this
I was not compensated for this
I would not have advised this
I do not like this
And worst of all, the number of people who've read my thesis has still not increased.
I did not ask for this
I did not consent to this
I did not approve of this
I was not compensated for this
I would not have advised this
I do not like this
And worst of all, the number of people who've read my thesis has still not increased.
June 3, 2025 at 1:54 PM
Quand on alertait sur le fait que Academia était un acteur privé, lucratif, parasite pour la recherche publique, qui commercialisait les données, on nous répondait souvent "oui, mais c'est carrément mieux que HAL par exemple, qui n'est pas intuitif".
Voilà le résultat...
Voilà le résultat...
Today, I discovered that my first research paper just hit 100 citations. I am happy to see that this method and the provided dataset for art analysis have been reused or inspired other works.
Weakly Supervised Object Detection in Artworks : openaccess.thecvf.com/content_ECCV...
Weakly Supervised Object Detection in Artworks : openaccess.thecvf.com/content_ECCV...
May 20, 2025 at 1:50 PM
Today, I discovered that my first research paper just hit 100 citations. I am happy to see that this method and the provided dataset for art analysis have been reused or inspired other works.
Weakly Supervised Object Detection in Artworks : openaccess.thecvf.com/content_ECCV...
Weakly Supervised Object Detection in Artworks : openaccess.thecvf.com/content_ECCV...
Reposted by Nicolas Gonthier
Il ne manque que 50000 signatures pour s'opposer à cette saloperie des âges obscurs que sont les "thérapies de conversion" dans toute l'UE.
eci.ec.europa.eu/043/public/#...
eci.ec.europa.eu/043/public/#...
European Citizens' Initiative
Give your support !
eci.ec.europa.eu
May 16, 2025 at 11:58 AM
Il ne manque que 50000 signatures pour s'opposer à cette saloperie des âges obscurs que sont les "thérapies de conversion" dans toute l'UE.
eci.ec.europa.eu/043/public/#...
eci.ec.europa.eu/043/public/#...
📍 𝗝𝗼𝗶𝗻 𝘂𝘀 𝗶𝗻 𝗡𝗮𝘀𝗵𝘃𝗶𝗹𝗹𝗲 #CVPR2025 !
𝗪𝗲'𝗹𝗹 𝗯𝗲 𝗽𝗿𝗲𝘀𝗲𝗻𝘁𝗶𝗻𝗴: HySCDG , a generative pipeline for creating a large hybrid semantic change detection for Earth Observation
🖼️ 𝗣𝗼𝘀𝘁𝗲𝗿 #187 Session 1,
Friday, June 13 10:30 - 12:30
📄 Paper: arxiv.org/abs/2503.15683
🔗 Project: yb23.github.io/projects/cywd/
𝗪𝗲'𝗹𝗹 𝗯𝗲 𝗽𝗿𝗲𝘀𝗲𝗻𝘁𝗶𝗻𝗴: HySCDG , a generative pipeline for creating a large hybrid semantic change detection for Earth Observation
🖼️ 𝗣𝗼𝘀𝘁𝗲𝗿 #187 Session 1,
Friday, June 13 10:30 - 12:30
📄 Paper: arxiv.org/abs/2503.15683
🔗 Project: yb23.github.io/projects/cywd/
The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generation
Bi-temporal change detection at scale based on Very High Resolution (VHR) images is crucial for Earth monitoring. This remains poorly addressed so far: methods either require large volumes of annotate...
arxiv.org
May 16, 2025 at 2:24 PM
📍 𝗝𝗼𝗶𝗻 𝘂𝘀 𝗶𝗻 𝗡𝗮𝘀𝗵𝘃𝗶𝗹𝗹𝗲 #CVPR2025 !
𝗪𝗲'𝗹𝗹 𝗯𝗲 𝗽𝗿𝗲𝘀𝗲𝗻𝘁𝗶𝗻𝗴: HySCDG , a generative pipeline for creating a large hybrid semantic change detection for Earth Observation
🖼️ 𝗣𝗼𝘀𝘁𝗲𝗿 #187 Session 1,
Friday, June 13 10:30 - 12:30
📄 Paper: arxiv.org/abs/2503.15683
🔗 Project: yb23.github.io/projects/cywd/
𝗪𝗲'𝗹𝗹 𝗯𝗲 𝗽𝗿𝗲𝘀𝗲𝗻𝘁𝗶𝗻𝗴: HySCDG , a generative pipeline for creating a large hybrid semantic change detection for Earth Observation
🖼️ 𝗣𝗼𝘀𝘁𝗲𝗿 #187 Session 1,
Friday, June 13 10:30 - 12:30
📄 Paper: arxiv.org/abs/2503.15683
🔗 Project: yb23.github.io/projects/cywd/
Reposted by Nicolas Gonthier
#CVPR2025 Sat June 14 (PM) ✨ Highlight
🛰️ AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities
@gastruc.bsky.social @nicaogr.bsky.social @loicland.bsky.social
📄 pdf: arxiv.org/abs/2412.14123
🌐 webpage: gastruc.github.io/anysat
🛰️ AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities
@gastruc.bsky.social @nicaogr.bsky.social @loicland.bsky.social
📄 pdf: arxiv.org/abs/2412.14123
🌐 webpage: gastruc.github.io/anysat
April 30, 2025 at 1:04 PM
#CVPR2025 Sat June 14 (PM) ✨ Highlight
🛰️ AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities
@gastruc.bsky.social @nicaogr.bsky.social @loicland.bsky.social
📄 pdf: arxiv.org/abs/2412.14123
🌐 webpage: gastruc.github.io/anysat
🛰️ AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities
@gastruc.bsky.social @nicaogr.bsky.social @loicland.bsky.social
📄 pdf: arxiv.org/abs/2412.14123
🌐 webpage: gastruc.github.io/anysat
Introducing HySCDG #CVPR2025, a generative pipeline for creating a large hybrid semantic change detection for Earth Observation using Stable Diffusion and ControlNet ! 🗺️🛩️
📄 Paper: arxiv.org/abs/2503.15683
📄 Paper: arxiv.org/abs/2503.15683
The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generation
Bi-temporal change detection at scale based on Very High Resolution (VHR) images is crucial for Earth monitoring. This remains poorly addressed so far: methods either require large volumes of annotate...
arxiv.org
April 28, 2025 at 4:48 PM
Introducing HySCDG #CVPR2025, a generative pipeline for creating a large hybrid semantic change detection for Earth Observation using Stable Diffusion and ControlNet ! 🗺️🛩️
📄 Paper: arxiv.org/abs/2503.15683
📄 Paper: arxiv.org/abs/2503.15683
Reposted by Nicolas Gonthier
We're hiring! IMAGINE @ École des Ponts (Paris area) is opening a 4-year "CV for X" researcher position:
– competitive salary
– no teaching load
– starting pkg ≈ 2 PhDs
– goal: impactful core AI + X (climate, biodiversity, robotics...)
Apply by May 31: imagine-lab.enpc.fr/wp-content/u...
– competitive salary
– no teaching load
– starting pkg ≈ 2 PhDs
– goal: impactful core AI + X (climate, biodiversity, robotics...)
Apply by May 31: imagine-lab.enpc.fr/wp-content/u...
April 24, 2025 at 3:02 PM
We're hiring! IMAGINE @ École des Ponts (Paris area) is opening a 4-year "CV for X" researcher position:
– competitive salary
– no teaching load
– starting pkg ≈ 2 PhDs
– goal: impactful core AI + X (climate, biodiversity, robotics...)
Apply by May 31: imagine-lab.enpc.fr/wp-content/u...
– competitive salary
– no teaching load
– starting pkg ≈ 2 PhDs
– goal: impactful core AI + X (climate, biodiversity, robotics...)
Apply by May 31: imagine-lab.enpc.fr/wp-content/u...
Reposted by Nicolas Gonthier
complete blog post is now live! more tips, and reframed into 2-step process: (1) get accepted by page 1, (2) avoid rejection with the rest. download both PDFs too.
maxwellforbes.com/posts/how-to...
maxwellforbes.com/posts/how-to...
April 11, 2025 at 9:35 PM
complete blog post is now live! more tips, and reframed into 2-step process: (1) get accepted by page 1, (2) avoid rejection with the rest. download both PDFs too.
maxwellforbes.com/posts/how-to...
maxwellforbes.com/posts/how-to...
Reposted by Nicolas Gonthier
"Early May"
bmvc2025.bmva.org/dates/
"The submission portal will be available from late-April, 2025"
bmvc2025.bmva.org/calls/call-f...
bmvc2025.bmva.org/dates/
"The submission portal will be available from late-April, 2025"
bmvc2025.bmva.org/calls/call-f...
The 36th British Machine Vision Conference 2025: Call for Papers
The website is for the 36th British Machine Vision Conference. 24th - 27th November 2025, Sheffield, UK.
bmvc2025.bmva.org
April 10, 2025 at 2:27 PM
"Early May"
bmvc2025.bmva.org/dates/
"The submission portal will be available from late-April, 2025"
bmvc2025.bmva.org/calls/call-f...
bmvc2025.bmva.org/dates/
"The submission portal will be available from late-April, 2025"
bmvc2025.bmva.org/calls/call-f...
Does anyone know the deadline for BMVC 2025 and the submission site ?
April 10, 2025 at 2:21 PM
Does anyone know the deadline for BMVC 2025 and the submission site ?
Reposted by Nicolas Gonthier
J'ai fait une réponse bien trop courte à la question de @nicolasherbeaux.bsky.social « A-t-on les moyens d'accueillir les chercheurs américains ».
Je vais faire un développement ici, parce que ça me parait important (et chiant, mais ça m'a réveillé à 5h donc il faut que ça sorte).
Je vais faire un développement ici, parce que ça me parait important (et chiant, mais ça m'a réveillé à 5h donc il faut que ça sorte).
Shrek Fiona GIF
ALT: Shrek Fiona GIF
media.tenor.com
March 30, 2025 at 8:21 AM
J'ai fait une réponse bien trop courte à la question de @nicolasherbeaux.bsky.social « A-t-on les moyens d'accueillir les chercheurs américains ».
Je vais faire un développement ici, parce que ça me parait important (et chiant, mais ça m'a réveillé à 5h donc il faut que ça sorte).
Je vais faire un développement ici, parce que ça me parait important (et chiant, mais ça m'a réveillé à 5h donc il faut que ça sorte).
Reposted by Nicolas Gonthier
🔥🔥🔥 CV Folks, I have some news! We're organizing a 1-day meeting in center Paris on June 6th before CVPR called CVPR@Paris (similar as NeurIPS@Paris) 🥐🍾🥖🍷
Registration is open (it's free) with priority given to authors of accepted papers: cvprinparis.github.io/CVPR2025InPa...
Big 🧵👇 with details!
Registration is open (it's free) with priority given to authors of accepted papers: cvprinparis.github.io/CVPR2025InPa...
Big 🧵👇 with details!
March 21, 2025 at 6:43 AM
🔥🔥🔥 CV Folks, I have some news! We're organizing a 1-day meeting in center Paris on June 6th before CVPR called CVPR@Paris (similar as NeurIPS@Paris) 🥐🍾🥖🍷
Registration is open (it's free) with priority given to authors of accepted papers: cvprinparis.github.io/CVPR2025InPa...
Big 🧵👇 with details!
Registration is open (it's free) with priority given to authors of accepted papers: cvprinparis.github.io/CVPR2025InPa...
Big 🧵👇 with details!