Áron Monszpart Profile
Áron Monszpart

@AMonszpart

Followers
199
Following
349
Media
2
Statuses
79

Staff Research Scientist @3rddimensionai Previously: @Niantic, intern @Adobe Computer Vision, Graphics and ML. Opinions are my own.

London, England
Joined March 2012
Don't wanna be here? Send us removal request.
@3rddimensionai
Third Dimension AI
1 month
We're heading to #ICCV25 next week! 🌺 Here's where you can find the Third Dimension team 👇
1
1
0
@leonard_bruns
Leonard Bruns
1 month
Happy to share the work from my internship at @nianticspatial: ACE-G, which we will present at ICCV next week in Hawaii 🌴 ACE-G introduces large-scale pre-training to previously mainly per-scene-optimized scene coordinate regressors. (1/n)
2
7
22
@tolgakart
Tolga Kart
2 months
I was at @foxglove Actuate this week and it really felt like a who’s who of physical AI. I truly enjoyed meeting some of the people I had been looking up to, and definitely made new friends. Congratulations to @adrianmacneil and team for bringing together such an impressive group
0
3
5
@MohammedAmr1
Mohamed Sayed
8 months
Splats are great, but wouldn’t it be wonderful if we could transform them into the stuff of dreams? Introducing our #CVPR2025 paper ✨Morpheus✨! Morpheus lets you change the shape and appearance of 3D Gaussian splats with a few words! https://t.co/16O5v18IRd (1/6)
2
56
239
@dantkz
Daniyar Turmukhambetov
1 year
Niantic is hiring PhD students for internships in 2025: https://t.co/COxxpbcVPq
Tweet card summary image
job-boards.greenhouse.io
0
10
32
@eric_brachmann
Eric Brachmann
1 year
We wrote a text on how we envision the future of visual mapping: https://t.co/sIUkXMooyl So far, we have trained ~50 million ACE networks. 😎 Together, that's 150 trillion parameters... Not bad! But the future lies in going from local small models to a global large model.
Tweet card summary image
nianticlabs.com
At Niantic, we are pioneering the concept of a Large Geospatial Model that will use large-scale machine learning to understand a scene and connect it to millions of other scenes globally.
3
32
195
@eric_brachmann
Eric Brachmann
1 year
We updated the #ACEZero repository to make it compatible with newer versions of @nerfstudioteam. We added some functions to make it easy to train Gaussian splats on top of ACE0. See our FAQ: "I want Gaussian splats from my images. What do I need to do?" https://t.co/jB8wAh38Fu
0
17
107
@eccvconf
European Conference on Computer Vision #ECCV2026
1 year
HUGE shoutout to our awesome #ECCV2024 🇮🇹 Program Chairs for all their efforts! @eliricci_ @gulvarol @orussakovsky @stefanroth @SattlerTorsten
2
5
71
@gui_ggh
Guillermo Garcia-Hernando
1 year
We'll be at poster 105 this afternoon! In the meantime, you can try an interactive DEMO of a lightweight mobile version of HandDGP directly on ANY device with a browser! https://t.co/FUuol80YAp #ECCV2024
Tweet card summary image
nianticresearch.8thwall.app
HandDGP ECCV 2024 demo
@gui_ggh
Guillermo Garcia-Hernando
1 year
👋Would you like more accurate 3D camera-space hand mesh predictions? Check our new #ECCV2024 work: "HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global Positioning". Project page: https://t.co/7PUrmVAn32 (1/5)
0
2
2
@gui_ggh
Guillermo Garcia-Hernando
1 year
We have released the code and model weights on https://t.co/tRHmypuRFm #ECCV2024
Tweet card summary image
github.com
[ECCV 2024] HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global Positioning - nianticlabs/HandDGP
@gui_ggh
Guillermo Garcia-Hernando
1 year
👋Would you like more accurate 3D camera-space hand mesh predictions? Check our new #ECCV2024 work: "HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global Positioning". Project page: https://t.co/7PUrmVAn32 (1/5)
0
4
14
@SattlerTorsten
Torsten Sattler
1 year
Attending @eccvconf and looking for PhD or postdoc positions in 3D reconstruction or visual localization? Happy to talk to you :)
2
22
88
@JeromeRevaud
Jerome Revaud
1 year
I had to try. Not too bad despite the many non-Lambertian surfaces 😉
3
5
68
@eric_brachmann
Eric Brachmann
1 year
#MapFreeReloc workshop in progress. The room is relatively small but maybe you can still fit in to hear Jakob Engel tell you about spatial AI. #ECCV2024
@eric_brachmann
Eric Brachmann
1 year
The #MapFreeReloc workshop next Monday at #ECCV2024 has such an incredible lineup of speakers... Jakob (@jajuengel), Vincent (@Vinc3nt_Leroy), Simon (@SimonLynen), Torsten (@SattlerTorsten), Shubham (@shubhtuls) and Victor (@viprad)! Schedule: https://t.co/EpZ8LkTQD3
1
4
31
@JeromeRevaud
Jerome Revaud
1 year
Having fun with MASt3R-SfM 😀 (paper should be on arXiv on Tuesday). (By the way, come see @Vinc3nt_Leroy 's talk tomorrow morning to the #MapFreeReloc workshop at #ECCV2024)
5
32
239
@eric_brachmann
Eric Brachmann
1 year
Are you looking forward to the presentation of MASt3R at #ECCV2024? Let me tell you a secret 🤫🤫🤫 MASt3R gets covered in an extended talk at the #MapFreeReloc workshop by @Vinc3nt_Leroy on Mon, and a poster too! Skip the line of the main conference, thank me later.
@Vinc3nt_Leroy
Vincent Leroy
1 year
And of course we'll also be there for the awesome #MapFreeReloc Workshop. This task really is the future: blending DL methods for scale and traditional relative pose estimation! And good news, there's still room for improvements... @JeromeRevaud @naverlabseurope @eric_brachmann
1
12
50
@eric_brachmann
Eric Brachmann
1 year
Catching the last days of summer in Saxon Switzerland. Filming random stuff. (#ACEZero + Splatfacto)
4
7
65
@eric_brachmann
Eric Brachmann
1 year
#ACEZero will be presented in pretty much exactly one week in oral session 2C at #ECCV2024 in Milano. Try the code now, and roast me with live questions! 🫣 https://t.co/2AXltyTuVe
Tweet card summary image
github.com
[ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation. - n...
@eric_brachmann
Eric Brachmann
2 years
📢A new learning-based approach to SfM: #ACEZero No img-to-img matching, optimises image-to-scene correspondences directly. Needs no pose priors. Works on unordered image sets. Efficiently handles thousands of images. Paper: https://t.co/Zc83YpoXpY Page: https://t.co/kutgb81eFV
1
3
53
@eric_brachmann
Eric Brachmann
1 year
Ahead of #ECCV2024, we held the #MapFreeReloc challenge. The winner is ... 🥁 🥇MASt3R. Congrats to @Vinc3nt_Leroy, Yohann, @JeromeRevaud for first place! No-one was able to beat MASt3R throughout the challenge duration. Nevertheless, we had amazing further submissions! 👇🧵
2
27
127