Jerome Revaud

AI researcher :: Computer vision :: 3D vision :: Team Lead :: Project Lead :: Naver Labs Europe. Views are my own

[Jerome Revaud @JeromeRevaud]

Not a paper, but certainly more important than a paper… at least to me

[Francesca Albanese, UN Special Rapporteur oPt @FranceskAlbs]

I have never felt so shaken.

Children are dying of hunger. Falling one after another, like petals of a dying flower. Under our watch.

How do you sleep, Presidents, Foreign Ministers, political leaders, diplomats, civil servants - doing nothing to stop Israel’s starvation campaign?

PS: Talking politics while dodging genocide perfectly meets the definition of doing nothing.

[Jerome Revaud @JeromeRevaud]

@chrisoffner3d Let me know if you find it
@grok can you help?

[Jerome Revaud @JeromeRevaud]

@jianyuan_wang @riverakid1 @Vinc3nt_Leroy Thanks Jianyuan. It’s nice to see there’s a sort of convergence in 3d vision towards scalable learning-based methods, and of course I’m not only talking about dust3r-like methods. One recent paper that blew my mind is rayzer 👇

[Zhenjun Zhao @zhenjun_zhao]

RayZer: A Self-supervised Large View Synthesis Model

@hanwenjiang1, @HaoTan5, @totoro97_, @Haian_Jin, @__yuezhao__, @Sai__Bi, @KaiZhang9546, @fujun_luan, Kalyan Sunkavalli, @qixing_huang, @geopavlakos

https://t.co/gnky66Al5P

[Jerome Revaud @JeromeRevaud]

Online reconstruction of ~400 sq meters in feed-forward regression only

[Vincent Leroy @Vinc3nt_Leroy]

RGB-SLAM becomes a single forward through the network with no optimization needed. We still need to only keep keyframes to avoid exploding the costs. We simply check the 3D overlap between views and memory, ensuring new keyframes discover enough novel content...

[Jerome Revaud @JeromeRevaud]

RT is a bit late but well

[Vincent Leroy @Vinc3nt_Leroy]

*3R posts are back! 🧵
Interested in SfM, RGB-SLAM or... both at the same time???
Come see MUSt3R @CVPR25 Friday morning, ExHall D Poster #82.
Jerome and Boris will be there to present how we can adapt DUSt3R to multiple views via a memory mechanism (and maybe do parkour?!)

[NAVER LABS Europe @naverlabseurope]

A teaser of the latest 3D DUSt3R based models we’re presenting at @cvprconference
Discover MUSt3R & Pow3R, universal encoder DUNE + research in navigation, vizloc, segmentation & human motion understanding!
All our #CVPR2025 papers are here
➡️ https://t.co/0tm1FEiNOG

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

MAST3R-based solution won IMC-2025!
https://t.co/fHZ3UoEWvu
@JeromeRevaud @Vinc3nt_Leroy

[Jerome Revaud @JeromeRevaud]

@jon_barron good one!

[Jerome Revaud @JeromeRevaud]

@wbjang11 @naverlabseurope @WeinzaepfelP @Vinc3nt_Leroy @LourdesAgapito here's one illustration of the new capabilities

[Wonbong Jang / Won @wbjang11]

Happy to introduce our new CVPR paper—Pow3R: Empowering Unconstrained 3D Reconstruction with Scene and Camera Priors : https://t.co/i9nvnhHxbE

Inspired by the amazing DUSt3R, which reconstructs 3D from just two unposed images, we explored:

(1/n)

[Jerome Revaud @JeromeRevaud]

@oodgnas @naverlabseurope @BDuisterhof @LojzeZust @WeinzaepfelP @Vinc3nt_Leroy Thanks 🙏

[Zhenjun Zhao @zhenjun_zhao]

Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors

@wbjang11, @WeinzaepfelP, @Vinc3nt_Leroy, @LourdesAgapito, @JeromeRevaud

tl;dr: DUSt3R with any optional input subset of camera intrinsics, pose and depthmaps

https://t.co/lmE3bXbPmA

[Zhenjun Zhao @zhenjun_zhao]

MUSt3R: Multi-view Network for Stereo 3D Reconstruction

Yohann Cabon, Lucas Stoffl, Leonid Antsfeld, @kgcs96, Boris Chidlovskii, @JeromeRevaud, @Vinc3nt_Leroy

tl;dr: make DUSt3R symmetric and iterative+multi-layer memory mechanism->multi-view DUSt3R

https://t.co/ncXvEsZvZC

[Jerome Revaud @JeromeRevaud]

@AjdDavison @eric_dexheimer @rmurai0610 Awesome work (and done really fast! MASt3R-SfM was only released during ECCV). Congratulations to all of you

[Andrew Davison @AjdDavison]

MASt3R-SLAM: it's easily the most robust dense monocular SLAM system I've ever seen, and also very accurate. Real-time, RGB only (no IMU), handles unknown focal length and zoom. More new videos coming soon @eric_dexheimer @rmurai0610. Paper and full info: https://t.co/pYL4U4LMIn

[Zhiwen(Aaron) Fan @zhiwen_fan_]

🚀 Our NeurIPS '24 work, Large Spatial Model (LSM), is here! LSM performs semantic 3D reconstruction in just 0.1s, processing unposed data via feed-forward 3D reconstruction.

👉It leverages large-scale 3D datasets with minimal annotations, defining a 3D latent space. We are continuously exploring how this explicit 3D representation can further enhance reasoning and robotic learning.

🔗 Try our online Gradio demo with your own data at https://t.co/FjGsPkcJ6h

#NeurIPS2024 #3DReconstruction

[Jerome Revaud @JeromeRevaud]

@ducha_aiki @Vinc3nt_Leroy thanks for the live coverage! 🙏

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

And colloquium is starting with @Vinc3nt_Leroy arguing we need one model to rule them all in 3D

[Jerome Revaud @JeromeRevaud]

Not 3D vision but interesting work by Gabriela and colleagues about explainability in CV

[Gabriela Csurka @kgcs96]

We presented the poster at the eXCV workshop at #ECCV2024 . Thank you to people stopping by. If you missed it and you are interested in explainability in CV (#xAI) here is our poster.

[Jerome Revaud @JeromeRevaud]

@junyi42 Great work!