Been waiting for the code release of DUSt3R? Wait no more, there it is! github.com/naver/dust3r Reminiscent of RayDiffusion (github.com/jasonyzhang/Ra…), we present a well behaved variant to Bundle Adjustment, this time with pointmaps.

Try the demo here: github.com/naver/dust3r.

Shuzhe Wang Jerome Revaud Chidlovskii Boris Vincent Leroy Witchcraft. 😄 I just ran it on my own images (after changing all mentions of CUDA to [device = "mps" if torch.backends.mps.is_available() else "cpu"]) and wow, this is super cool! 🤩

Jerome Revaud 😳

Another convenient usage of DUSt3R (kind of anecdotal): While looking for a rental apartment on airbnb for my vacations, i noticed I had difficulty grasping the layout and space of the apartment based on photos alone. Solution: put all photos in DUSt3R and voila :)

done, DUSt3R now first of the leaderboard! research.nianticlabs.com/mapfree-reloc-…

Instant Video-to-3D with DUST3R Dust3r generates a whole 3D scene from just a couple of images. What if it could: 1. Accept a VIDEO 2. Extract the video frames 3. Turn them into 3D? So added a Gradio Video Component. Here's me generating 3D from a video cc: NAVER LABS Europe

Sth I find fascinating with DUSt3R is its uncanny ability to perform auto-calibration... even with single images. Is it precise? Quite so, as you can see below. This challenges the prevailing notion that single-image calibration is ill-posed (ambiguous & under-constrained)!

Some more impressive 3D reconstruction examples from #DUSt3R kindly prepared by our boss ;-) Martin Humenberger NAVER LABS Europe

📣We are hiring in 🇫🇮! We are looking for motivated applicants to do a PhD in AI/ML-related topics. Please, spread the word.

The bar is too high to reach…😕

better faster stronger 3DGS, thanks MrNeRF for the recommendation x.com/i/broadcasts/1…

🚀Excited to introduce the open-source 🌟Awesome-DUSt3R🌟, a curated list of DUSt3R-related (dust3r.europe.naverlabs.com) 📄papers, 📚blog posts, 🎥videos, etc. Join us on this journey and contribute to the ever-growing list at github.com/ruili3/awesome…!

Awesome inspiring talk from Jerome Revaud !!! So delighted by the positive response of everyone about our work for the past 4 years ! And what a crowd!

Let's all welcome MASt3R, the new *St3R model that just came to this world! My laptops Quadro RTX 3000 (6GB) can process ~100 images in 10 min, that's pretty nice for mapping!

Thank you so much, Jianyuan Jianyuan@CVPR 2025 ! Big congrats on the Best Paper - VGGT is well deserved and truly inspiring! 🏆 I really appreciate the kind words about DUSt3R! It’s been a pleasure getting to know you these past months - excited to see where your research goes next🚀