iiinova — where your digital self keeps evolving

Bart Duisterhof @bardienus.bsky.social · 19/09/2025

RaySt3R was accepted to NeurIPS! Check out the HuggingFace demo for image to 3D in cluttered scenes huggingface.co/spaces/bartd...

052

Bart Duisterhof @bardienus.bsky.social · 12/06/2025

In "hearing the slide"👂 (led by @yuemin-mao.bsky.social ) we estimate *loss* of contact with a contact microphone, and use it to learn dynamic constraints.⚡ It allows moving multiple intricate objects🍷 efficiently, even objects that would otherwise be hard to grasp. fast-non-prehensile.github.io

fast-non-prehensile.github.io

Hearing the Slide: Acoustic-Guided Constraint Learning for Fast Non-Prehensile Transport

040

Bart Duisterhof @bardienus.bsky.social · 06/06/2025

🔗 Project Website: rayst3r.github.io 📄 arXiv: arxiv.org/abs/2506.05285 🚀 Code: github.com/Duisterhof/... 🤗 HF Demo: Coming (very) soon! @CMU_Robotics @SCSatCMU @nvidia @NVIDIAAI @NVIDIARobotics

github.com

GitHub - Duisterhof/rayst3r

Contribute to Duisterhof/rayst3r development by creating an account on GitHub.

020

Bart Duisterhof @bardienus.bsky.social · 06/06/2025

Big thanks to the awesome contributors to this project!👏 Jan Oberst, @bowenwen_me, @BirchfieldStan, @RamananDeva and @jeff_ichnowski. Also thanks to OctMAE author @s1wase, @nvidia for sponsoring compute 🖥️, and the scientists at @naverlabseurope for the inspiration! 🧗‍♂️

110

Bart Duisterhof @bardienus.bsky.social · 06/06/2025

We also study the impact of the confidence threshold on reconstruction quality. Our ablations suggest setting a higher confidence threshold improves accuracy, while limiting completeness and edge-bleeding. Users can tune the threshold for application-specific requirements 🎛️.

100

Bart Duisterhof @bardienus.bsky.social · 06/06/2025

We evaluate RaySt3R against the baselines on synthetic and real-world datasets. The results suggest RaySt3R achieves zero-shot generalization to the real world, and outperforms all baselines by up to 44% in 3D chamfer distance 🚀.

100

Bart Duisterhof @bardienus.bsky.social · 06/06/2025

We train RaySt3R by curating a new dataset, for a total of 12 million views 📷 with Objaverse and GSO objects. The ablations 🔍 suggest that more and more diverse data improves RaySt3R's performance. RaySt3R does not require GT meshes, paving the way for training on real-world data.

100

Bart Duisterhof @bardienus.bsky.social · 06/06/2025

💡 Our key insight is that 3D object shape completion can be recasted as a novel-view synthesis problem. RaySt3R takes a masked RGB-D image as input, and predicts depth maps and object masks for novel views. We query multiple views and merge the predictions into a consistent point cloud.

110

Bart Duisterhof @bardienus.bsky.social · 06/06/2025

We focus on multi-object 3D shape completion for robotics. Robots are commonly equipped with a RGB-D camera 📷, but their measurements are noisy and incomplete. Using only DINOv2 features 🦖 as pretraining, we train a new model (RaySt3R) to produce accurate geometry.

110

Bart Duisterhof @bardienus.bsky.social · 06/06/2025

Imagine if robots could fill in the blanks in cluttered scenes. ✨ Enter RaySt3R: a single masked RGB-D image in, complete 3D out. It infers depth, object masks, and confidence for novel views, and merges the predictions into a single point cloud. rayst3r.github.io

1243

Bart Duisterhof @bardienus.bsky.social · 26/03/2025

Do you think Europe will take the opportunity? The Netherlands is even cutting research funds under the new administration... It feels like there are still significantly more opportunities in the US.

010

Bart Duisterhof @bardienus.bsky.social · 26/03/2025

Thanks Chris! This was a push with the entire dust3r team @naverlabseurope.bsky.social, congrats everyone!

080

Reposted by Bart Duisterhof

International Conference on 3D Vision @3dvconf.bsky.social · 26/03/2025

The Best Student Paper Award goes to MASt3R-SfM! #3DV2025

0428

Reposted by Bart Duisterhof

Uksang Yoo @uksang.bsky.social · 17/03/2025

🎉Excited to share that our paper was a finalist for best paper at #HRI2025! We introduce MOE-Hair, a soft robot system for hair care 💇🏻💆🏼 that uses mechanical compliance and visual force sensing for safe, comfortable interaction. Check our work: moehair.github.io @cmurobotics.bsky.social 🧵1/7

1105

Reposted by Bart Duisterhof

Zhenjun Zhao @ericzzj.bsky.social · 04/03/2025

MUSt3R: Multi-view Network for Stereo 3D Reconstruction Yohann Cabon, Lucas Stoffl, Leonid Antsfeld, Gabriela Csurka, Boris Chidlovskii, Jerome Revaud, @vincentleroy.bsky.social tl;dr: make DUSt3R symmetric and iterative+multi-layer memory mechanism->multi-view DUSt3R arxiv.org/abs/2503.01661

1254

Bart Duisterhof @bardienus.bsky.social · 31/01/2025

Great news, CMU's Center for Machine Learning and Health (CMLH) decided to fund another year of our research! If you're a PhD student at CMU, consider applying for the next iterations of the fellowship - the funding is generous and relatively unconstrained :)

030

Bart Duisterhof @bardienus.bsky.social · 05/12/2024

Is the book just as good/better than the show for "The 3 body problem"?

200

Reposted by Bart Duisterhof

CMU Robotics Institute @cmurobotics.bsky.social · 26/11/2024

Watch Professor Jeff Ichnowski's RI seminar talk: "Learning for Dynamic Robot Manipulation of Deformable and Transparent Objects" 🦾🤖 @jeff-ichnowski.bsky.social closed out our Fall seminar series. Keep an eye out for the Spring schedule in the new year! www.youtube.com/watch?v=DvvF...

youtube.com

RI Seminar : Jeffrey Ichnowski : Learning for Dynamic Robot Manipulation of Deformable...

YouTube video by CMU Robotics Institute

0152

Reposted by Bart Duisterhof

Sarvesh Patil @nagababa.bsky.social · 23/11/2024

Intro Post Hello World! I'm a 2nd year Robotics PhD student at CMU, working on distributed dexterous manipulation, accessible soft robots and sensors, sample efficient robot learning, and causal inference. Here are my cute robots: PS: Videos are old and sped up. They move slower in real-world :3

0153

Reposted by Bart Duisterhof