🚀 Our new paper on #PolyGNN, a graph neural network for 3D building reconstruction from point clouds, is out now! 🌍🏙️ It's scalable, accurate, and ready for real-world applications.
paper: https://t.co/uE9lwdusmy
code: https://t.co/6hWh0Se6JR
#AI#EO#3D#UrbanModeling
Excited to dive into #MachineLearning for #EarthObservation? 🌱🌐 Check out this free MOOC: "Introduction to Machine Learning for Earth Observation" being part of #ML4Earth: https://t.co/6QBxxDZnJi
link to project: https://t.co/O83kqgFCzS
Happy to share that my PhD student Sugandha Doda successfully defended her PhD thesis on "Population Estimation Utilizing Earth Observation Data"! warmest congrats to Dr. Doda for this great achievement! 🌍📊 #PhDDefense#PopulationEstimation#Congratulations#AI4EO
🚀 Perspectives on Earth and Climate Foundation Models! 🌍 Check out our new paper, "On the Foundations of Earth and Climate #FoundationModels," where we define 11 essential features to guide research towards the ideal FM.
👉 Read it here: https://t.co/717gegfCjL
Our team is looking for a senior scientist/manager who is interested in working with us to help shape the profile of our lab in teaching and research:
https://t.co/bty02nE37p
Keynote presentations are from @xiaoxiang_zhu on Machine Learning for Earth Observation & Beyond, and from Martin Schultz on what will come next in #AI for Weather models, Climate models & Earth system models.
Full programme and to register by 3 May ➡️ https://t.co/I5YpoyJQB0
Happy to share that our "Contrastive Pretraining for Visual Concept Explanations of Socioeconomic Outcomes" paper (https://t.co/dOFvGZjwSL) was accepted at the #EarthVision workshop at #CVPR2024.
with @Alevering1, Lars Penning, Dario Oliveira @diego_marcos_g, and @xiaoxiang_zhu
How significant would #urbanization impact urban tree coverage? Jianhua extracted #UrbanTreeCoverage of more than 800 cities in North America via #AI4EO, from which prevalent positive indirect effect of urbanization on UTC was revealed.
Link to our paper: https://t.co/MvKLvegeWN
wish for one #EO#FoundationModel for all types of input data with different modalities #SAR#Optical, with different # of bands or even for unseen sensors? Check our new #NeuralPlasticity Inspired model -#DOFA.
paper: https://t.co/SwcqzTFTKD
code: https://t.co/xlMq5IHfNU
Curious about #Referring#RemoteSensing Image #Segmentation? It aims at segmenting out the objects from a RS image, given natural language expression. We introduce this new #NLP in #EO task, a dedicated dataset #RefSegRS, and a #LGCE module.
paper: https://t.co/BMPA1fW2Ca
Interested in getting an overview on #building extraction from #RemoteSensing imagery? Qingyu complied a comprehensive survey, recently published @IEEE_GRSS#TGRS - RS offers a perspective to complement incomplete #OSM building data.
Link to paper: https://t.co/GMt5OtXxRq