iiinova — where your digital self keeps evolving

Reposted by Alexandre Boulch

valeo.ai @valeoai.bsky.social · 25/11/2025

Need pixel-level features from your backbone (DINOv3, CLIP, RADIO, FRANCA...)? 🚀Introducing NAF: A universal, zero-shot feature upsampler. It turns low-res ViT features into pixel-perfect maps. -⚡ Model-agnostic -🥇 SoTA results -🚀 4× faster than SoTA -📈 Scales up to 2K res

1163

Reposted by Alexandre Boulch

Nicolas Audebert @nshaud.bsky.social · 09/07/2025

Pour les collègues francophones, vous saviez que le FID était tout cassé ? Moi non plus. Pourtant, si on s'y prend bien, on peut calculer le FID avec moins de 1000 images. J'en parlerai au GRETSI fin août : hal.science/hal-05142942 👀

hal.science

Évaluation des générateurs d'images à partir de peu d'exemples : calculer le FID avec 10 fois moins d'images, c'est possible

La distance Inception de Fréchet (Fréchet Inception Distance ou FID) est une métrique standard pour l'évaluation des modèles génératifs images. Construite sur la distance de Wasserstein, le FID mesure...

043

Reposted by Alexandre Boulch

valeo.ai @valeoai.bsky.social · 25/06/2025

How to make your DINOv2 excel at dense in-context scene understanding tasks. Check out DIP an effective post-training strategy by @ssirko.bsky.social @spyrosgidaris.bsky.social ‬ @vobeckya.bsky.social ‬@abursuc.bsky.social and Nicolas Thome 👇 #iccv2025

062

Reposted by Alexandre Boulch

Tetiana Martyniuk🇺🇦@ ICIP’26🇫🇮 @t-martyniuk.bsky.social · 25/06/2025

We just released the code of #LiDPM, go ahead and play with it (and don't forget to star 🤭🤩)! Training and inference code available, along with the model checkpoint. Github repo: github.com/astra-vision... #IV2025

github.com

GitHub - astra-vision/LiDPM: [IV 2025, Oral] Official code of "LiDPM: Rethinking Point Diffusion for Lidar Scene Completion"

[IV 2025, Oral] Official code of "LiDPM: Rethinking Point Diffusion for Lidar Scene Completion" - astra-vision/LiDPM

163

Reposted by Alexandre Boulch

Tetiana Martyniuk🇺🇦@ ICIP’26🇫🇮 @t-martyniuk.bsky.social · 23/06/2025

Presenting our project #LiDPM in the afternoon oral session at #IV2025! Project page: astra-vision.github.io/LiDPM/ w/ @gillespuy.bsky.social, @alexandreboulch.bsky.social, Renaud Marlet, Raoul de Charette Also, see our poster at 3pm in the Caravaggio room and AMA 😉

1103

Reposted by Alexandre Boulch

Tetiana Martyniuk🇺🇦@ ICIP’26🇫🇮 @t-martyniuk.bsky.social · 23/06/2025

Okay that was stressful 🥲

171

Reposted by Alexandre Boulch

Paul Couairon @paulcouairon.bsky.social · 16/06/2025

🚀Thrilled to introduce JAFAR—a lightweight, flexible, plug-and-play module that upsamples features from any Foundation Vision Encoder to any desired output resolution (1/n) Paper : arxiv.org/abs/2506.11136 Project Page: jafar-upsampler.github.io Github: github.com/PaulCouairon...

1266

Reposted by Alexandre Boulch

valeo.ai @valeoai.bsky.social · 24/02/2025

🚗 Ever wondered if an AI model could learn to drive just by watching YouTube? 🎥👀 We trained a 1.2B parameter model on 1,800+ hours of raw driving videos. No labels. No maps. Just pure observation. And it works! 🤯 🧵👇 [1/10]

1257

Reposted by Alexandre Boulch

Andrei Bursuc @abursuc.bsky.social · 27/01/2025

This amazing team ❤️

1193

Reposted by Alexandre Boulch

Loïc Landrieu @loicland.bsky.social · 19/12/2024

Check out our new work with @gastruc.bsky.social and @nicaogr.bsky.social and Clément Mallet! The one-stop shop for multimodal Earth Observation 🤩

0123

Reposted by Alexandre Boulch

Loïc Landrieu @loicland.bsky.social · 09/12/2024

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🧵👇

1278

Reposted by Alexandre Boulch

F. Güney @fguney.bsky.social · 05/12/2024

I could easily spend an afternoon looking at the results of this paper: motionmodes.github.io or this paper: rollingdepth.github.io or this paper: romosfm.github.io vision is cool 😎

motionmodes.github.io

Motion Modes: What Could Happen Next?

Motion Modes is the first training-free method to generate multiple plausible yet distinct motions for a given object, disentangled from the motion of other objects, camera and other scene changes, fr...

1208

Alexandre Boulch @alexandreboulch.bsky.social · 05/12/2024

At INRIA Paris for @anhquancao.bsky.social for his PhD defense. Subject is Learning Semantics and Geometry for Scene Understanding. anhquancao.github.io

060