🏹 Job alert: 4-year position as Research Fellow in Computer Vision for X at @ImagineEnpc Goal: impactful core AI + X (climate, biodiversity, robotics...) 📍 Paris ➡️ Apply by May 31 https://t.co/0ABhGRuG4A

#CVPR2025 Workshop (EarthVision) Wed June 11 📜 CoDEx: Combining Domain Expertise for Spatial Generalization in Satellite Image Analysis @Elt_Vincent @loiclandrieu 📄 pdf: https://t.co/2U2vs5iHnu 🌐 webpage:

#CVPR2025 Workshop (EarthVision) Wed June 11 ⛏️ Detecting Looted Archaeological Sites from Satellite Image Time Series @Elt_Vincent @iconem @LaDafa_afg 📄 pdf: https://t.co/9abmWBqFnf 🌐 webpage: https://t.co/EY1htN7rGQ

#CVPR2025 Sun June 15 (PM) 🧩 RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges @thibaut_loiseau @GBourmaud 📄 pdf: https://t.co/a0Cl6kdikO

#CVPR2025 Sat June 14 (PM) ✨ Highlight 🛰️ AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities @g_astruc @NicaoGr @loiclandrieu 📄 pdf: https://t.co/yvLge8S4jN 🌐 webpage: https://t.co/WVMl2ZkPXG

#CVPR2025 Sat June 14 (PM) 🎬 Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs @Lucas__Ventura, @AntoineYang2, @CordeliaSchmid, @gulvarol 📄 pdf: https://t.co/qvISH5B0VU 🌐 webpage: https://t.co/Tq0KLKTtsW 💻 code: https://t.co/Q8Ute5Yh8b

#CVPR2025 Sat June 14 (PM) 🌍 Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation @nico_dufour @VickyKalogeiton @david_picard @loiclandrieu 📄 pdf: https://t.co/QdNdUKl47v 🌐 webpage: https://t.co/zcS48L3Mo7

#CVPR2025 Sat June 14 (PM) 🛠️ PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction @stekovic_sinisa Arslan Artykov Stefan Ainetter Mattia D'Urso Friedrich Fraundorfer 📄 pdf: https://t.co/ox6e9j1y3M 🌐 webpage: https://t.co/GSw2Hey7jI

#CVPR2025 Fri June 13 (PM) ✨ Highlight 🍵 MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views @antoine_guedon @kyoto_vision 📄 pdf: https://t.co/ZCKKd51i9l 🌐 webpage: https://t.co/AbMWkfX7W9

#CVPR2025 Fri June 13 (PM) 🤟Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues Youngjoon Jang, @HRaajesh, @LiliMomeni, @gulvarol, Andrew Zisserman @Oxford_VGG 📄 pdf: https://t.co/XcW3uIkdpV 🌐 webpage: https://t.co/oLxBeAIlvH

#CVPR2025 Fri June 13 (AM) ✨Highlight 🌳Open-Canopy: Towards Very High Resolution Forest Monitoring Fajwel Fogel, Yohann Perron, Martin Schwartz, Nikola Besic, Alexandre d'Aspremont @loiclandrieu @ciais_philippe 📄 pdf: https://t.co/sslFKdYbtl 🌐 webpage: https://t.co/gXdvguCozc

Looking forward to #CVPR2025! We will present the following papers:

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:

🧩Excited to share our paper "RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges" https://t.co/7vbufXdITE accepted to #CVPR2025! We created a benchmark that systematically evaluates image matching methods across well-defined geometric difficulty levels.

🧵 1/3 Many at #CVPR2024 & #ECCV2024 asked what would be next in our workshop series. We're excited to announce "How to Stand Out in the Crowd?" at #CVPR2025 Nashville - our 4th community-building workshop featuring this incredible speaker lineup! 🔗 https://t.co/MVFTAiRRz4

Don't miss out on the premiere event bridging computer vision and Earth Observation! This year at #CVPR2025

Very happy to be at @c2rmf with Mathieu Aubry @ImagineEnpc to present our platforms dedicated to AI applied to historical and cultural documents #AIKON #Arkindex @_Teklia_

🤔 What if embedding multimodal EO data was as easy as using a ResNet on images? Introducing AnySat: one model for any resolution (0.2m–250m), scale (0.3–2600 hectares), and modalities (choose from 11 sensors & time series)! Try it with just a few lines of code:

🌍 Guessing where an image was taken is a hard, and often ambiguous problem. Introducing diffusion-based geolocation—we predict global locations by refining random guesses into trajectories across the Earth's surface! 🗺️ Paper, code, and demo: https://t.co/pNRFZk9NYP

Airborne #LiDAR has revolutionized the study of ancient rainforest civilizations by seeing through dense canopies. Yet archaeologists still annotate their data manually. Introducing Archaeoscape at #NeurIPS2024—the first deep learning-scale, open-access archaeological dataset🧵👇