We have had an _amazing_ week in Banff at the BIRS “3D Generative Models” workshop Thank to BIRS for hosting us! birs.ca/events/2023/5-…

Introducing FastViT, fast, super-small, general purposes vision transformers running at ~ 1ms on mobile. Code and pre-trained models are live. github.com/apple/ml-fastv… #ICCV2023

Presenting FineRecon, a SOTA method that directly regresses scene-level 3D geometry from posed multi-view images without any iterative optimization. Come to our #ICCV2023 poster in Foyer Sud - 079 at 10.30am. code: github.com/apple/ml-finer…

🎶Time to start NeRFing audio. Introducing NVAS3D for novel acoustic synthesis in 3D scenes. Watch with AirPods. arxiv: arxiv.org/abs/2310.15130 code: github.com/apple/ml-nvas3d

Just in time for the holidays, we are releasing some new software today from Apple machine learning research. MLX is an efficient machine learning framework specifically designed for Apple silicon (i.e. your laptop!) Code: github.com/ml-explore/mlx Docs: ml-explore.github.io/mlx/build/html…

SKEL received Honorable Mention for Best Paper at SIGGRAPH Asia ➡️ Hong Kong. We combine the #SMPL body model with a biomechanical skeleton; a win for graphics & biomechanics. Congrats Marilyn Keller, Keenon Werling, Soyon Shin, Scott Delp, Sergi Pujades, Karen Liu. skel.is.tue.mpg.de

Congrats to my lead authors at Apple on getting two great papers accepted to #ICLR2024: - Ahmed Elhag with Manifold Diffusion Fields (arxiv.org/abs/2305.15586) - Xiaoming Zhao with Dynamic Novel View Synthesis (arxiv.org/abs/2310.08587)

Are you interested in SOTA compact CLIP models? 🚀🚀 Check out our open-sourced repo for a family of MobileCLIP models, including a ViT-B@224 with 77.2% IN-top1 accuracy. More highlights in 🧵 Paper (appearing in CVPR 2024): arxiv.org/abs/2311.17049 Repo: github.com/apple/ml-mobil…

Infinite-resolution diffusion, again, from apple 🍎 bros. They are releasing so many interesting works, im becoming apple stan Its from dec 2024, WHY WAS NOT aware of this work?