COP GEN Beta
π¦
Official demo for the COP-GEN-Beta model
Mikolaj Czerkawski
mikonvergence
AI & ML interests
None yet
Recent Activity
new activity
24 minutes ago
mikonvergence/COP-GEN-Beta:Apply for community grant: Academic project (gpu)
updated
a Space
25 minutes ago
mikonvergence/COP-GEN-Beta
liked
a Space
2 days ago
mikonvergence/MESA
Organizations
mikonvergence's activity
Apply for community grant: Academic project (gpu)
4
#1 opened 2 days ago
by
mikonvergence
updated
a
Space
25 minutes ago
liked
a
Space
2 days ago
posted
an
update
2 days ago
Post
1355
ππππ ποΈ πππ±π-πππ¬ππ πππ«π«ππ’π§ π ππ§ππ«πππ’π¨π§ π¦π¨πππ₯
MESA is a novel generative model based on latent denoising diffusion capable of generating 2.5D representations (co-registered colour and depth maps) of terrains based on text prompt conditioning.
Work developed by Paul BorneβPons ( @NewtNewt ) during his joint internship at
Adobe & ESA, and in collaboration with asterisk labs.
ποΈ ππ«π¨π£πππ πππ π : https://paulbornep.github.io/mesa-terrain/
π ππ«ππ©π«π’π§π : https://arxiv.org/abs/2504.07210
π€ ππ¨πππ₯ πππ’π π‘ππ¬ : NewtNewt/MESA
πΎ πππππ¬ππ : Major-TOM/Core-DEM
π§π»βπ»βππ¨ππ : https://github.com/PaulBorneP/MESA
ππ ππ©πππ: mikonvergence/MESA
MESA is a novel generative model based on latent denoising diffusion capable of generating 2.5D representations (co-registered colour and depth maps) of terrains based on text prompt conditioning.
Work developed by Paul BorneβPons ( @NewtNewt ) during his joint internship at
Adobe & ESA, and in collaboration with asterisk labs.
ποΈ ππ«π¨π£πππ πππ π : https://paulbornep.github.io/mesa-terrain/
π ππ«ππ©π«π’π§π : https://arxiv.org/abs/2504.07210
π€ ππ¨πππ₯ πππ’π π‘ππ¬ : NewtNewt/MESA
πΎ πππππ¬ππ : Major-TOM/Core-DEM
π§π»βπ»βππ¨ππ : https://github.com/PaulBorneP/MESA
ππ ππ©πππ: mikonvergence/MESA
- 2 replies
authored
a
paper
2 days ago
upvoted
a
paper
2 days ago
liked
a
model
2 days ago
updated
a
Space
3 days ago
Apply for community grant: Academic project (gpu)
2
#1 opened 4 days ago
by
mikonvergence
published
2
Spaces
4 days ago
updated
a
dataset
12 days ago
updated
a
Space
3 months ago
reacted to
mkluczek's
post with ππ₯
4 months ago
Post
1749
First Global and Dense Open Embedding Dataset of Earth! π π€
Introducing the Major TOM embeddings dataset, created in collaboration with CloudFerro S.A. πΆ and Ξ¦-lab at the European Space Agency (ESA) π°οΈ. Together with @mikonvergence and JΔdrzej S. Bojanowski, we present the first open-access dataset of Copernicus embeddings, offering dense, global coverage across the full acquisition areas of Sentinel-1 and Sentinel-2 sensors.
π‘ Highlights:
π Data: Over 8 million Sentinel-1 & Sentinel-2 images processed, distilling insights from 9.368 trillion pixels of raw data.
π§ Models: Foundation models include SigLIP, DINOv2, and SSL4EO.
π¦ Scale: 62 TB of raw satellite data processed into 170M+ embeddings.
This project delivers open and free vectorized expansions of Major-TOM/README datasets, setting a new standard for embedding releases and enabling lightweight, scalable ingestion of Earth Observation (EO) data for countless applications.
π€ Explore the datasets:
Major-TOM/Core-S2L1C-SSL4EO
Major-TOM/Core-S1RTC-SSL4EO
Major-TOM/Core-S2RGB-DINOv2
Major-TOM/Core-S2RGB-SigLIP
π Check paper: Global and Dense Embeddings of Earth: Major TOM Floating in the Latent Space (2412.05600)
π» Code notebook: https://github.com/ESA-PhiLab/Major-TOM/blob/main/05-Generate-Major-TOM-Embeddings.ipynb
Introducing the Major TOM embeddings dataset, created in collaboration with CloudFerro S.A. πΆ and Ξ¦-lab at the European Space Agency (ESA) π°οΈ. Together with @mikonvergence and JΔdrzej S. Bojanowski, we present the first open-access dataset of Copernicus embeddings, offering dense, global coverage across the full acquisition areas of Sentinel-1 and Sentinel-2 sensors.
π‘ Highlights:
π Data: Over 8 million Sentinel-1 & Sentinel-2 images processed, distilling insights from 9.368 trillion pixels of raw data.
π§ Models: Foundation models include SigLIP, DINOv2, and SSL4EO.
π¦ Scale: 62 TB of raw satellite data processed into 170M+ embeddings.
This project delivers open and free vectorized expansions of Major-TOM/README datasets, setting a new standard for embedding releases and enabling lightweight, scalable ingestion of Earth Observation (EO) data for countless applications.
π€ Explore the datasets:
Major-TOM/Core-S2L1C-SSL4EO
Major-TOM/Core-S1RTC-SSL4EO
Major-TOM/Core-S2RGB-DINOv2
Major-TOM/Core-S2RGB-SigLIP
π Check paper: Global and Dense Embeddings of Earth: Major TOM Floating in the Latent Space (2412.05600)
π» Code notebook: https://github.com/ESA-PhiLab/Major-TOM/blob/main/05-Generate-Major-TOM-Embeddings.ipynb
- 1 reply
commented
a
paper
4 months ago
upvoted
a
paper
4 months ago
authored
a
paper
4 months ago
liked
2
datasets
4 months ago