
What if you could turn any number of photos (3, 8, 15, or even 60) into one clean 3D surface (pts & mesh) with Flow Matching? Check out our new work, Surflo: Consistent 3D Surface Flow Model with Global State. 🧵 1/n 🔗anttwo.github.io/surflo/

Computer Vision team of LIGM/A3SI @EcoledesPonts ParisTech (ENPC)

What if you could turn any number of photos (3, 8, 15, or even 60) into one clean 3D surface (pts & mesh) with Flow Matching? Check out our new work, Surflo: Consistent 3D Surface Flow Model with Global State. 🧵 1/n 🔗anttwo.github.io/surflo/

Excited to share that MIRO is accepted to ICML 2026 @icmlconf ! 🎉 We introduce multi-reward conditioned training for text-to-image. By training on continuous reward scores, we can simply condition on HIGH REWARDS at inference to guarantee top-tier, aligned outputs.

Excited to share my work as a Student Researcher at Google Zurich: UniGeoCLIP! 🌍🚀 W/ Eduard Trulls, Jan Hosang, @loiclandrieu & @pesarlin, we built a framework aligning 5 geospatial modalities in one space. Presented at EarthVision @ #CVPR2026. 🧵👇

🏹 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 imagine-lab.enpc.fr/wp-conte…

#CVPR2025 Workshop (EarthVision) Wed June 11 📜 CoDEx: Combining Domain Expertise for Spatial Generalization in Satellite Image Analysis @Elt_Vincent @loiclandrieu 📄 pdf: arxiv.org/abs/2504.19737 🌐 webpage: sites.google.com/view/codexe…

#CVPR2025 Workshop (EarthVision) Wed June 11 ⛏️ Detecting Looted Archaeological Sites from Satellite Image Time Series @Elt_Vincent @iconem @LaDafa_afg 📄 pdf: arxiv.org/abs/2409.09432 🌐 webpage: github.com/ElliotVincent/DAF…

#CVPR2025 Sun June 15 (PM) 🧩 RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges @thibaut_loiseau @GBourmaud 📄 pdf: arxiv.org/abs/2502.19955

#CVPR2025 Sat June 14 (PM) ✨ Highlight 🛰️ AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities @g_astruc @NicaoGr @loiclandrieu 📄 pdf: arxiv.org/abs/2412.14123 🌐 webpage: gastruc.github.io/anysat

#CVPR2025 Sat June 14 (PM) 🎬 Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs @Lucas__Ventura, @AntoineYang2, @CordeliaSchmid, @gulvarol 📄 pdf: arxiv.org/abs/2504.00072 🌐 webpage: imagine.enpc.fr/~lucas.ventu… 💻 code: github.com/lucas-ventura/cha…

#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: arxiv.org/abs/2412.06781 🌐 webpage: nicolas-dufour.github.io/plo…

#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: arxiv.org/abs/2404.10620 🌐 webpage: vevenom.github.io/pytorchgeo…

#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: arxiv.org/abs/2412.06767 🌐 webpage: anttwo.github.io/matcha/

#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: arxiv.org/abs/2501.09754 🌐 webpage: robots.ox.ac.uk/~vgg/researc…

#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: arxiv.org/abs/2407.09392 🌐 webpage: github.com/fajwel/Open-Canop…

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: imagine-lab.enpc.fr/wp-conte…