Adriano Cardace

Computer Vision Research Scientist at the Enigma Project, Stanford University

[Allan Zhou @AllanZhou17]

Coming to #ICLR2024: what's the best way to extract information from implicit neural representations (INRs)?

We show that tri-planes alone are enough to effectively classify or segment 3D objects in neural fields. 🧵

[Adriano Cardace @AdrianoCardace]

Can we process hybrid neural fields to solve downstream tasks such as 3D object classification/segmentation? In this new work, we show that using hybrid representations such as tri-planes can provide many advantages over neural fields parametrized as MLP:

https://t.co/M6D956TF7V

[Luigi Di Stefano @LuigiDi77998956]

Signals are networks so networks are data and so networks can process other networks to understand and generate signals. Puzzled ? Check out out our #iclr2023 paper (https://t.co/gzl3ImWZOV)
Deep Learning on Implicit Neural Representations of Shapes

[Adriano Cardace @AdrianoCardace]

Happy to release the code for our new paper "Self-Distillation for Unsupervised 3D Domain Adaptation" accepted at WACV2023!
Code and paper can be found here:
https://t.co/Dq8NInzW5q
A big thanks to my colleagues @pierluigi92 and @RSpezialetti

[Peyman Milanfar @docmilanfar]

“Yeah, but they haven’t demonstrated they can go *up* the stairs.”

https://t.co/LEnFJDqjvs

[_ @Amookeena]

La situazione sta un pelino sfuggendo di mano

#Chiellini
#Saka