🍏 Open Source Vision from #Apple 🍏

👉CVNets: open-source (not a joke) lib for neural vision.

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅PyTorch-based neural lib. for vision
✅Train 2−4× longer w/ augmentations
✅Plug-and-play components for CV
✅Source code under a custom license

More: https://bit.ly/39d1dSj

🔥One Millisecond Backbone. Fire!🔥

👉MobileOne by #Apple: efficient mobile backbone with inference <1 ms on #iPhone12!

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅75.9% top-1 accuracy on ImageNet
✅38× faster than MobileFormer net
✅Classification, detection & segmentation
✅Source code & model soon available!

More: https://bit.ly/3tsT7f2

🍏NeuMan: Human NeRF in the wild🍏

👉#Apple opens a novel human pose/view from just a single in-the-wild video

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅No extra devices/annotations
✅Both Human (novel poses) + Scene
✅E2E SMPL optimization + error-corr.
✅Applications such as "telegathering"

More: https://bit.ly/3K4iTO6

🍏 f-DM: Diffusion Models by Apple 🍏

👉Spectacular work by #Apple on DMs: HQ generation with better efficiency and semantic

😎Review https://bit.ly/3Tils2u
😎Project https://jiataogu.me/fdm/
😎Paper arxiv.org/pdf/2210.04955.pdf

🧱 MobileBrick: #3D object on mobile 🧱

👉#Apple (+Oxford) exploiting #LEGO bricks to open the most precise #3D dataset ever. Suitable for mobile #AR

😎Review https://bit.ly/3ZqbiAh
😎Paper arxiv.org/pdf/2303.01932.pdf
😎Project code.active.vision/MobileBrick/
😎Code github.com/ActiveVisionLab/MobileBrick

🔥 #Apple Co-Motion is out! 🔥

👉Apple unveils a novel approach for detecting & tracking detailed 3D poses of multiple people from single monocular stream. Temporally coherent predictions in crowded scenes with hard poses & occlusions. New SOTA, 10x faster! Code & Models released only for research💙

👉Review https://t.ly/-86CO
👉Paper https://lnkd.in/dQsVGY7q
👉Repo https://lnkd.in/dh7j7N89