Jerome Revaud

512 posts

Jerome Revaud banner
Jerome Revaud

Jerome Revaud

@JeromeRevaud

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

Grenoble, France Katılım Haziran 2023
111 Takip Edilen1.7K Takipçiler
Jerome Revaud
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 arxiv.org/abs/2505.00702

English
1
0
26
1.9K
Jianyuan
Jianyuan@jianyuan_wang·
Just touched down from the air back to solid ground😄 We're honored to receive the Best Paper Award this year, while I want to give a special shout-out to the authors of the brilliant paper Dust3R: Shuzhe Wang (@riverakid1), Vincent Leroy (@Vinc3nt_Leroy), Yohann Cabon, Boris Chidlovskii, and Jerome Revaud (@JeromeRevaud). It is Dust3R that first showcased the power of scaling up 3D learning (by aggregating academic datasets) and trusting data! This paved the way for our research🥰 On a personal note, I only met Shuzhe Wang (@riverakid1) two months ago, but it was immediately clear he's both insightful and genuinely awesome 😊 Any team would be incredibly lucky to hire him! Finally, huge thanks to all—old friends and new—for an amazing CVPR experience.
Jianyuan@jianyuan_wang

The must-read paper for me this month. Quite impressive. And it seems vggsfm can also benefit from similar ideas.

English
2
4
131
18K
Jerome Revaud retweetledi
NAVER LABS Europe
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 ➡️ tinyurl.com/4z79ujce
English
2
35
229
14.2K
Jon Barron
Jon Barron@jon_barron·
Why do people use softplus? Calling two transcendental functions just to get a non-negative number with smooth gradients seems like overkill. Here's a simple all-algebraic alternative ("squareplus"?) that's twice as fast and seems to do the job.
Jon Barron tweet media
English
29
115
945
0
Jerome Revaud retweetledi
Wonbong Jang / Won
Wonbong Jang / Won@wbjang11·
Happy to introduce our new CVPR paper—Pow3R: Empowering Unconstrained 3D Reconstruction with Scene and Camera Priors : arxiv.org/pdf/2503.17316 Inspired by the amazing DUSt3R, which reconstructs 3D from just two unposed images, we explored: (1/n)
Wonbong Jang / Won tweet media
English
3
40
211
17K
Jerome Revaud retweetledi
Zhenjun Zhao
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 arxiv.org/abs/2503.01661
Zhenjun Zhao tweet mediaZhenjun Zhao tweet mediaZhenjun Zhao tweet mediaZhenjun Zhao tweet media
English
1
10
109
5K
Jerome Revaud retweetledi
Andrew Davison
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: edexheim.github.io/mast3r-slam
Riku Murai@rmurai0610

Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation. Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map. With @eric_dexheimer*, @AjdDavison (*Equal Contribution)

English
7
76
542
32.2K
Jerome Revaud retweetledi
Zhiwen(Aaron) Fan
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 largespatialmodel.github.io #NeurIPS2024 #3DReconstruction
English
3
63
308
43.7K
Junyi Zhang
Junyi Zhang@junyi42·
Excited to share MonST3R! -- a simple way to estimate geometry from unposed video of dynamic scene We achieve competitive results on several downstreams (video depth, camera pose) and believe this is a promising step toward feed-forward 4D reconstruction monst3r-project.github.io
English
22
137
727
131.4K