Originally posted by IEEE ComputerSociety / @ComputerSociety: http://nitter.platypush.tech/ComputerSociety/status/1671602398366932993#m

#metaai showing off at #cvpr23 exhibit floor

#ieee

Check out "Panoptic Lifting for 3D Scene Understanding with Neural Fields" #CVPR23 highlight!

Given only posed RGB images of a scene, we optimize a panoptic radiance field representing color, depth, semantics, and instances at any point in space.

Great work by Yawar Siddiqui in collaboration with Angela Dai, Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder.

Project: https://nihalsid.github.io/panoptic-lifting/
Code: https://github.com/nihalsid/panoptic-lifting
Video: https://youtu.be/QtsiL-6rSuM

Excited to talk about our #CVPR23 paper, "Investigating Data Replication in #Diffusion Models" at @ml_collective tomorrow! Drop by if you want to learn more about this topic!

⏰ - Mar 31, 1 pm Eastern
💻 - https://mlcollective.org/dlct/
📃 - https://arxiv.org/abs/2212.03860

#MachineLearning

NICE! High-Res Facial Appearance Capture from Polarized Smartphone Images 🤳

This approach uses a smartphone with a cheap polarization foil to capture facial textures in dark settings to then create photo-realistic 3D #DigitalHumans 👉https://dazinovic.github.io/polface/

#AI #CVPR23 #CVPR2023 #Computervision #DeepLearning