VincentLepetit (@vincentlepetit2) 's Twitter Profile
VincentLepetit

@vincentlepetit2

ID: 1338118857865695233

calendar_today13-12-2020 13:49:39

50 Tweet

238 Followers

212 Following

Imagine-ENPC (@imagineenpc) 's Twitter Profile Photo

@captnloic Björn Michele Alexandre Boulch Gilles Puy Nicolas Courty BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds. Corentin Sautier, Gilles Puy, Alexandre Boulch, VincentLepetit, Renaud Marlet. pdf: arxiv.org/pdf/2310.17281… code: github.com/valeoai/BEVCon…

@captnloic <a href="/Bjoern_Michele/">Björn Michele</a> <a href="/AlexandreBoulch/">Alexandre Boulch</a> <a href="/gillespuy/">Gilles Puy</a> <a href="/nicolas_courty/">Nicolas Courty</a> BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds.
Corentin Sautier, <a href="/gillespuy/">Gilles Puy</a>, <a href="/AlexandreBoulch/">Alexandre Boulch</a>, <a href="/VincentLepetit2/">VincentLepetit</a>, Renaud Marlet.
pdf: arxiv.org/pdf/2310.17281…
code: github.com/valeoai/BEVCon…
valeo.ai (@valeoai) 's Twitter Profile Photo

Meet BEVContrast: a surprisingly simple self-supervised learning (SSL) method for automotive Lidar point clouds, with no pre-processing, consistent hyperparams across datasets and architectures, and strong performance boosts in both low-shot and full label regimes #3DV2024 🧵 1/

Meet BEVContrast: a surprisingly simple self-supervised learning (SSL) method for automotive Lidar point clouds, with no pre-processing, consistent hyperparams across datasets and architectures, and strong performance boosts in both low-shot and full label regimes #3DV2024 🧵 1/
VincentLepetit (@vincentlepetit2) 's Twitter Profile Photo

Procedural modeling is a popular tool for many applications, but extremely challenging to recover from images. With PyTorchGeoNodes, we introduce a PyTorch differentiable module for rendering procedural modeling programs. vevenom.github.io/pytorchgeonode… Sinisa Stekovic

Procedural modeling is a popular tool for many applications, but extremely challenging to recover from images. With PyTorchGeoNodes, we introduce a PyTorch differentiable module for rendering procedural modeling programs.

vevenom.github.io/pytorchgeonode… 
<a href="/stekovic_sinisa/">Sinisa Stekovic</a>
VincentLepetit (@vincentlepetit2) 's Twitter Profile Photo

We also show how to use our PyTorchGeoNodes module for reconstructing 3D objects from images in the form of interpretable modelling programs. Work done with Sinisa Stekovic, Stefan Ainetter, Mattia D'Urso, Friedrich Fraundorfer vevenom.github.io/pytorchgeonode…

We also show how to use our PyTorchGeoNodes module for reconstructing 3D objects from images in the form of interpretable modelling programs.

Work done with <a href="/stekovic_sinisa/">Sinisa Stekovic</a>, Stefan Ainetter, Mattia D'Urso, Friedrich Fraundorfer
 
vevenom.github.io/pytorchgeonode…
Loic Landrieu (@loiclandrieu) 's Twitter Profile Photo

Can you guess where these photos were taken? GeoGuessr players have taken this skill to the extreme, but how good can an AI perform? Introducing OpenStreetView-5M 🌍, the first open-access and global-scale dataset of street view images. 🔗 Links and 🤖 demo below 👇 #CVPR2024

Can you guess where these photos were taken? <a href="/geoguessr/">GeoGuessr</a> players have taken this skill to the extreme, but how good can an AI perform? Introducing OpenStreetView-5M 🌍, the first open-access and global-scale dataset of street view images. 
🔗 Links and 🤖 demo below 👇
#CVPR2024
David Picard (@david_picard) 's Twitter Profile Photo

Good news! Expect to see many offers from my colleagues at IPParis and Imagine-ENPC . (Myself I don't know, I'm trying to show down a little bit)

vannguyen (@vannguyen_ng) 's Twitter Profile Photo

📢 Benchmark for 6D Object Pose Estimation 📢 BOP challenge 24 has been opened! bop.felk.cvut.cz/challenges/bop… Results to be presented at the R6D workshop at #ECCV2024 Details in comments below👇

📢 Benchmark for 6D Object Pose Estimation 📢

BOP challenge 24 has been opened!

bop.felk.cvut.cz/challenges/bop…

Results to be presented at the R6D workshop at #ECCV2024

Details in comments below👇
Imagine-ENPC (@imagineenpc) 's Twitter Profile Photo

#CVPR2024 Wed 19 (PM) SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering Antoine Guédon VincentLepetit pdf: arxiv.org/abs/2311.12775 webpage: anttwo.github.io/sugar/ code: github.com/Anttwo/SuGaR

Imagine-ENPC (@imagineenpc) 's Twitter Profile Photo

#CVPR2024 Thu 20 (PM) NOPE: Novel Object Pose Estimation from a Single Image vannguyen Thibault GROUEIX Georgy Ponimatkin,   Yinlin Hu,  Renaud Marlet,  Mathieu Salzmann VincentLepetit pdf: arxiv.org/pdf/2303.13612 web: nv-nguyen.github.io/nope/ code: github.com/nv-nguyen/nope

Imagine-ENPC (@imagineenpc) 's Twitter Profile Photo

#CVPR2024 Thu 20 (AM) GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence vannguyen Thibault GROUEIX Mathieu Salzmann VincentLepetit pdf: arxiv.org/abs/2311.14155 webpage: nv-nguyen.github.io/gigaPose/ code: github.com/nv-nguyen/giga…

#CVPR2024 Thu 20 (AM)
GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence
<a href="/vannguyen_ng/">vannguyen</a> <a href="/thibaultgroueix/">Thibault GROUEIX</a> Mathieu Salzmann <a href="/VincentLepetit2/">VincentLepetit</a>
pdf: arxiv.org/abs/2311.14155
webpage: nv-nguyen.github.io/gigaPose/
code: github.com/nv-nguyen/giga…
Bryan Morse (@bryanmorse) 's Twitter Profile Photo

Kostas Daniilidis Lucas Beyer (bl16) Peyman Milanfar Animesh Garg #CVPR2025 Data from the CVPR 2024 PCs suggests that a cap of 25 would affect 616 paper submissions. That might not seem like much compared to the total volume of submissions, but 616 papers x 3 reviews/paper x ~6 papers/reviewer means more than 300 reviewers worth of time saved.

MrNeRF (@janusch_patas) 's Twitter Profile Photo

Code dropped: github.com/Anttwo/Frosting "[ECCV '24] Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering"

Antoine Guédon (@antoine_guedon) 's Twitter Profile Photo

#ECCV2024 #Blender If you're interested in high-quality Gaussian Splatting representations that can be edited and animated in Blender without a single line of code, Please come to our Oral Presentation of our ECCV2024 paper Gaussian Frosting on Oct2 at 1:40PM! Thread (1/n) 🧵

Yoshitomo Matsubara (@yoshitomo_cs) 's Twitter Profile Photo

Having served as Technical Chair for CVPR 2024, I was appointed to serve as Technical Chair for - CVPR 2025 - 2027 - ICCV 2025, 2027, and 2029 I am so excited to work for #CVPR2025 & #ICCV2025 and keep improving the review systems! 🔥🔥

Having served as Technical Chair for CVPR 2024, I was appointed to serve as Technical Chair for
- CVPR 2025 - 2027
- ICCV 2025, 2027, and 2029

I am so excited to work for <a href="/CVPR/">#CVPR2025</a> &amp; <a href="/ICCVConference/">#ICCV2025</a>  and keep improving the review systems! 🔥🔥
Martin Vetterli (@martinvetterli) 's Twitter Profile Photo

Time to leave a channel that has moved from informative and balanced to partisan and divisive. When money drives the public discourse, we know trouble lies ahead. Hey Kekius Maximus, remember Citizen Kane? en.wikipedia.org/wiki/Citizen_K…

Time to leave a channel that has moved from informative and balanced to partisan and divisive.
When money drives the public discourse, we know trouble lies ahead.
Hey <a href="/elonmusk/">Kekius Maximus</a>, remember Citizen Kane?
en.wikipedia.org/wiki/Citizen_K…
Siyu Tang @VLG-ETHZ (@siyutang3) 's Twitter Profile Photo

#CVPR2025 We have provided a few clarifications regarding the OpenReview account creation deadline, author modifications, dual submissions, and other related topics: cvpr.thecvf.com/Conferences/20… #CVPR2025 Fuxin Li Phillip Isola

#CVPR2025 (@cvpr) 's Twitter Profile Photo

Make sure to check out the latest #CVPR2025 Clarifications/FAQs (November 7, 2024). cvpr.thecvf.com/Conferences/20…

View Dependent (@viewdependent) 's Twitter Profile Photo

Curious about Radiance Field to Mesh research? Our next guest is Antoine Guédon, the author behind groundbreaking 3DGS-to-Mesh papers like SuGaR and Gaussian Frosting. Join us here, this Thursday at 3pm EST / 9pm CET 👇 youtube.com/@ViewDependent…