I took my parents to see it, my mom even cried! She liked it a lot.
I liked it but with a small shortcoming that it was a bit like a fairytale: with his driving style heβd get 12 penalty points in the super license easily within those 9 races π
29.06.2025 14:53 β π 1 π 0 π¬ 1 π 0
Did you like it?
29.06.2025 07:52 β π 1 π 0 π¬ 1 π 0
LiDPM is a collaboration between Inria and @valeoai.bsky.social, couldn't have done it without the support of my amazing supervisors @alexandreboulch.bsky.social, @gillespuy.bsky.social, Renaud Marlet and Raoul de Charette!
25.06.2025 20:07 β π 0 π 1 π¬ 0 π 0
We show that "vanilla" diffusion can be applied to large-scale (here - lidar) non-normalized point clouds.
LiDPM
β does not require any additional regularization,
β inherently extends to unconditional scene generation,
β outperforms "local" diffusion for scene completion on SemanticKITTI.
25.06.2025 20:05 β π 0 π 0 π¬ 1 π 0
We just released the code of #LiDPM, go ahead and play with it (and don't forget to star π€π€©)!
Training and inference code available, along with the model checkpoint.
Github repo: github.com/astra-vision...
#IV2025
25.06.2025 20:05 β π 6 π 3 π¬ 1 π 0
Itβs indeed a particular way to visualize the data :)
25.06.2025 11:04 β π 0 π 0 π¬ 1 π 0
One author with 14 submissions π€―
#iv2025
25.06.2025 10:54 β π 0 π 0 π¬ 1 π 0
30% of the papers were coming from Germany π€―
France - 5%
#iv2025
25.06.2025 10:52 β π 0 π 0 π¬ 1 π 0
Some #IV2025 statistics:
1/3 of all submissions were uploaded on the last day π
25.06.2025 10:50 β π 1 π 0 π¬ 1 π 0
On one hand you might think βThe conference destinations that are not exotic enough are not as coolβ.
But let me just tell you: I feel like Iβm at a wedding in Bukovyna rn, and I mean it in the best way possible! Such an amazing reception and beautiful Romanian folk music :) #iv2025
24.06.2025 17:33 β π 3 π 0 π¬ 0 π 0
And a really great poster session afterwards! So many relevant questions, I was thrilled to share the details of our work, thanks for stopping by. #iv2025
23.06.2025 16:39 β π 2 π 0 π¬ 0 π 0
Okay that was stressful π₯²
23.06.2025 11:18 β π 7 π 1 π¬ 1 π 0
Presenting our project #LiDPM in the afternoon oral session at #IV2025!
Project page: astra-vision.github.io/LiDPM/
w/ @gillespuy.bsky.social, @alexandreboulch.bsky.social, Renaud Marlet, Raoul de Charette
Also, see our poster at 3pm in the Caravaggio room and AMA π
23.06.2025 10:12 β π 10 π 3 π¬ 1 π 1
Multi-sensor fusion review paper presented by Dr. Ziran Wang.
#IV2025
22.06.2025 13:12 β π 0 π 0 π¬ 0 π 0
Feels like home π
22.06.2025 07:47 β π 1 π 0 π¬ 0 π 0
Dr. Ignacio Alvarez overviewing Generative AI for synthetic scenario generations, automated HD mapping, behavior of traffic agents, and world modeling.
#IV2025
22.06.2025 07:03 β π 1 π 0 π¬ 1 π 0
Day 1 of #IV2025 in Cluj-Napoca - letβs go!
Today is the Workshops day.
#autonomousDriving #autonomousVehicles #computerVision #AI
22.06.2025 06:05 β π 3 π 0 π¬ 1 π 0
Presenting LiDPM today at #CVPRinParis, such a great poster session, many new acquaintances and curious questions! #cvpr #cvpr2025
Next stop: #IV2025.
06.06.2025 13:14 β π 3 π 0 π¬ 0 π 0
Our paper "LiDPM: Rethinking Point Diffusion for Lidar Scene Completion" got accepted to IEEE IV 2025!
tldr: LiDPM enables high-quality LiDAR completion by applying a vanilla DDPM with tailored initialization, avoiding local diffusion approximations.
Project page: astra-vision.github.io/LiDPM/
28.04.2025 10:18 β π 12 π 4 π¬ 0 π 1
there should be or*
I donβt launch training on inference (what would that even mean?), but you can definitely see that I lack some sleep π΅βπ«
21.01.2025 21:09 β π 0 π 0 π¬ 0 π 0
me π«
21.01.2025 21:07 β π 1 π 0 π¬ 0 π 0
You realize that you became a slave of your research project when you canβt go to bed without launching some training on inference scripts - otherwise the GPUs will be shamelessly idle for the whole night.
21.01.2025 21:04 β π 10 π 0 π¬ 2 π 0
No, Iβm just dropping the ideas in case any product manager of Bluesky notices your post :)
06.01.2025 16:36 β π 1 π 0 π¬ 0 π 0
I think overall it would be a great feature to just "tag ppl" in a post, not make their handle part of the post itself.
smth like tagging a person in the IG post, or many other social media platforms. yes, it won't be a part of the story -> limits storytelling, but sometimes a simple tag is enough.
06.01.2025 15:36 β π 3 π 0 π¬ 2 π 0
I use this:
bsky.app/profile/t-ma...
02.12.2024 15:03 β π 0 π 0 π¬ 0 π 0
i liked the part about
- is it fun to be famous?
- you get used to it.
...
- but you never get used to being ignored.
02.12.2024 13:47 β π 1 π 0 π¬ 0 π 0
As long as I donβt see Muskβs nonsense claims after one full scroll - Iβm in a right place π
29.11.2024 19:10 β π 3 π 0 π¬ 1 π 0
great list! :)
29.11.2024 12:36 β π 1 π 0 π¬ 0 π 0
Removed Β«DiscoverΒ» feed for good now, currently keeping these four, but flagging Β«MutualsΒ» as potentially redundant for now.
What do your feeds look like?
27.11.2024 23:30 β π 1 π 0 π¬ 0 π 0
Computer Vision & Machine Learning researcher at NAVER LABS europe
she/her - https://dlarlus.github.io/
PhD student at IMAGINE (ENPC) and GeoVic (Ecole Polytechnique). Working on image generation.
http://nicolas-dufour.github.io
IntΓ©ressΓ© par : les maths, la physique, l'informatique, l'Γ©conomie, les relations internationales, les sciences en gΓ©nΓ©ral
AI & CV scientist, CEO at @kyutai-labs.bsky.social
3D Vision and Robotics - PostDoc @ Stanford
https://francisengelmann.github.io/
Cofounded and lead PyTorch at Meta. Also dabble in robotics at NYU.
AI is delicious when it is accessible and open-source.
http://soumith.ch
Associate Professor in EECS at MIT. Neural nets, generative models, representation learning, computer vision, robotics, cog sci, AI.
https://web.mit.edu/phillipi/
Secular Bayesian.
Professor of Machine Learning at Cambridge Computer Lab
Talent aficionado at http://airetreat.org
Alum of Twitter, Magic Pony and Balderton Capital
Senior Research Manager at NVIDIA. Prev professor at TUM. Computer vision mostly. Views are my own.
Research Scientist at DeepMind. Opinions my own. Inventor of GANs. Lead author of http://www.deeplearningbook.org . Founding chairman of www.publichealthactionnetwork.org
he/him; Researcher at NAVER LABS Europe. Greek, resident a Barcelona. https://www.skamalas.com/
Google Chief Scientist, Gemini Lead. Opinions stated here are my own, not those of Google. Gemini, TensorFlow, MapReduce, Bigtable, Spanner, ML things, ...
Prof. @notredame.bsky.social. IEEE Computer Society PAMI TC Chair. Computer Vision Foundation CTO. Artificial Intelligence + Digital Humanities + History of Technology. wjscheirer.com
Professor for CS at the Tuebingen AI Center and affiliated Professor at MIT-IBM Watson AI lab - Multimodal learning and video understanding - GC for ICCV 2025 - https://hildekuehne.github.io/