3D computer vision and ML for AR and robotics, @Google and TU Munich
Zürich
- Tweets 117
- Following 191
- Followers 2,705
- Likes 170
📣 Google/ETH PhD position available
The group of Prof Schindler at ETH offers a fully funded PhD position in collaboration with our team at Google on the topic of 3D computer vision and generative models.
For more details (including how to apply):
jobs.ethz.ch/job/view/JOPG_e…
44
223
28,853
2022 Google Zurich internship call!
If you are:
- a brilliant PhD student in CV/ML with top-tier publications (Neurips/ICML/ICCV/CVPR/..)
- interested in a 2022 Google research internship in the vibrant Zurich environment
- actively working on 3D comput…lnkd.in/dvTWAPdW
33
107
Hiring Computer Vision experts!
We are looking for CV experts to grow our Google applied research team in Mountain View and Zurich.
Our team works at the intersection of research and product to solve challenging real problems an…lnkd.in/dNZDB4bn lnkd.in/dcRPzMPt
2
15
90
Excited about the work we'll present at #ICCV2023 on "Robust monocular depth estimation under challenging conditions". A simple but effective way to deal with various weather/illumination conditions, applicable to most depth ML solutions in AD and beyond: md4all.github.io
9
57
2,423
The next edition of 3DV, the main research summit in 3D Computer Vision, will take place in March 2024 in a very special location. Proud to be part of it as PC with @taiyasaki and @SiyuTang3
📢📢📢 Excited to co-chair 3DV 2024 with Siyu Tang @SiyuTang3 and Federico Tombari @fedassa
Smaller conferences are where you create the networking that will last a lifetime.
1
7
54
8,917
Very excited about this collaboration with Andreas and MPI Tübingen on 3D GenAI. Looking forward to receiving your application.
4
37
7,197
Amazing result from our computer vision team at TUM CAMP. Go CAMP Chair :) lnkd.in/dzW_aVPz
35
proud to have contributed to this launch with our team, leveraging CV and ML to bring more understanding of geometry and math on Google Search/Lens
New features on Search and Lens to help learners get a deeper understanding of math and science topics on Search, including step-by-step explanations and solutions for math problems, help with physics word problems + new 3D models of science topics.
blog.google/products/search/…
35
3,632
If you are still around at #iccv23 come meet us at 3.15pm at the Google booth for 3d computer vision demos on nerf and scene understanding
Visit the #ICCV2023 Google booth today at 3:30 PM for a Q&A session on the limitations of employing neural implicit representations for real world applications. Don’t miss the opportunity to learn about Google research contributions toward this goal.
32
3,269
If you are at NeurIPS, don't forget to stop by this really cool poster on open-set 3d instance segmentation ;)
Today @efedele16 and I will present our work OpenMask3D at @NeurIPSConf 🎷
Visit our poster to learn more about OpenMask3D or to chat with us!
📍 Great Hall & Hall B1+B2 (level 1) #906
🕰️ 10:45-12:45
🌎 openmask3d.github.io
@FrancisEngelman @fedassa @mapo1
2
28
2,653
At #icml2022 (starting today) @JanisPostels from our team will present our recent work on deterministic uncertainty methods (DUMs).
Will be presenting our work "On the Practicality of Deterministic Epistemic Uncertainty" next week at #ICML2022 in Baltimore.
If you are interested checkout our paper or visit us at our poster on
Tue Jul 19 between 06:30 PM & 08:30 PM @ Hall E 506
arxiv.org/abs/2107.00649
28
At #ECCV2022 we'll present "Implicit Neural Representations for image compression". We show INRs are a promising tool for this task when powered by meta-learning.
Paper: arxiv.org/abs/2112.04267
Code: github.com/YannickStruempler…
With: @JanisPostels Y. Strümpler Ren Yang @lucvangool
1
3
26
Thanks to @FrancisEngelman, OpenNeRF is now available in Nerfstudio:
docs.nerf.studio/nerfology/m…
You can now try out open-set 3D semantic segmentation directly on NeRF representations from within Nerfstudio.
With @mapo1 @mi_niemeyer et al.
2
21
11,113
Congrats Ege and all co-authors for winning this award - go scene graphs!
🎉 Extremely honored to share that our MICCAI 2022 work, 4D-OR, its subsequent publication in IJCARS, "Holistic OR domain modeling: a semantic scene graph approach," has won the 1st Prize in the IJCARS-MICCAI 2022 Best Paper Award! 🏆
#IJCARS #MICCAI @MICCAI_Society
1
1
20
2,651
Fantastic result from the chair of Applied mechanics at TUM. We're honored to be part of this collaboration where we get to power Lola the humanoid with our semantic SLAM perception tech #tum #ai #SPECTRUM lnkd.in/d46f5kR
1
2
20
Our work on Variational Transformer Networks for layout generation got featured on the Google AI blog. The work will be presented at CVPR21 on June 24th and a pre-release is available on arXiv.
Blog post:
Official Tweet: https:/…lnkd.in/dSuZVFx lnkd.in/dBgXeRp
3
18
Congrats Prune and collaborators for having SPARF selected as highlight at #CVPR2023 !
So happy that our paper SPARF got a #CVPR2023 highlight! It is the result of my internship at #Google in @fedassa team.
SPARF: Neural Radiance Fields from Sparse and Noisy Poses
Arxiv: arxiv.org/abs/2211.11738
Website: prunetruong.com/sparf.github…
Code coming very soon!
1/n
18
2,490
Our poster on uncertainty estimation for neural networks presented today at the NeurIPS Bayesian DL meetup (poster F13)
arxiv.org/abs/2012.03082
bayesiandeeplearning.org/
1
16
Great accomplishment from our team at CAMP, TUM! More details on the accepted papers to follow up soon. Looking forward to seeing you in Vancouver! lnkd.in/edmFmGB2
13
1,153
If you work on scene graphs and/or graph representations for computer vision, you should not miss this ICCV23 workshop :)
📣Exciting news #2! Join us at the 1st workshop on Scene Graphs and Graph Representation Learning @sg2rl @ICCVConference
Amazing keynotes feat. @drfeifei @lucacarlone1 & more ↓
Papers & abstracts by Jul 25
Best Paper Prize!
sg2rl.github.io
w/@fedassa @azadef @NassirNavab
2
11
1,955
Our work on Compositional Zero Shot Learning using graph embeddings - a collaboration across MPI, U.Tübingen, TUM and Google to be presented at #CVPR21
Check out our #CVPR21 paper ‘Learning Graph Embeddings for Compositional Zero-shot Learning’ joint work with @ferjadnaeem @xyongqin and @fedassa
Paper: arxiv.org/pdf/2102.01987.pdf
Code: github.com/ExplainableML/czs…
11
Very happy to share that 5 of our papers got accepted at #eccv2020, of which 3 as orals (top 2% this year). Kudos to all my awesome co-authors across Google, TUM, Stanford, Oxford, Chalmers, Tsinghua (among others) for the great work and results. More det…lnkd.in/dZDq8AM
1
9
My TedX on 3D computer vision and machine learning is finally out.. might be interesting if you want to teach your robot something new. #ml #computervision #autonomousdriving #robotics lnkd.in/dQqd2Qx
3
8
This Thu (1.20pm UTC+1) we will present our #ECCV2020 Oral: "Self6D: Self-Supervised Monocular 6D Object Pose Estimation", by G. Wang, F. Manhardt, J. Shao, X. Ji, N. Navab and myself.
Arxiv: arxiv.org/abs/2004.06468
Video: piped.video/watch?v=bEtzjb8f…
Code: github.com/THU-DA-6D-Pose-Gr…
1
5
This week at #iccv2021 we will present our newest work for monocular 6D object pose estimation - a collaboration between Google, TUM and Tsinghua. See you at the virtual booth :) lnkd.in/gQcrKgN4
7
New capsule work from Geoff and team
Our new paper "𝐔𝐧𝐬𝐮𝐩𝐞𝐫𝐯𝐢𝐬𝐞𝐝 𝐩𝐚𝐫𝐭 𝐫𝐞𝐩𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 𝐛𝐲 𝐅𝐥𝐨𝐰 𝐂𝐚𝐩𝐬𝐮𝐥𝐞𝐬" is out arxiv.org/abs/2011.13920
TL;DR: are newborns exposed to 14 million (i.e. ImageNet) labeled images? No! They learn by observing motion... in an unsupervised fashion
5
Google released the open source TensorFlow-3D codebase for 3D object detection/scene understanding (including interfaces to 3D datasets)
github.com/google-research/g…
1
6
Our CVPR2020 paper on "Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions" is out #cvpr2020 #computervision #deeplearning lnkd.in/e-NhERE
1
1
2
3DV24 will follow the ECCV’22 approach and only present papers on-site when at least one of the authors is on-site to present the paper. If no author of an accepted paper can participate on-site, their paper will still be published in proceedings, but won't be presented on-site
1
29
live now on the Google Open Source blog google-opensource.blogspot.d…
3
We are all that stands between civilized society... and college students #pdhcomics phdcomics.com/comics.php?f=1… via @phdcomics
1