AI with Papers - Artificial Intelligence & Deep Learning
15.4K subscribers
140 photos
253 videos
14 files
1.33K links
All the AI with papers. Every day fresh updates about #DeepLearning, #MachineLearning, LLMs and #ComputerVision

Curated by Alessandro Ferrari | https://www.linkedin.com/in/visionarynet/

#artificialintelligence #machinelearning #ml #AI
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
🎹🎹 Learning Piano in #AR 🎹🎹

πŸ‘‰PianoVision (on #META #Quest2) accelerates the piano learning via Passthrough #AR & hand tracking

𝐇𝐒𝐠𝐑π₯𝐒𝐠𝐑𝐭𝐬:
βœ…Sheet Insight to learn sight-read
βœ…MIDI keyboard connectivity
βœ…Air piano for no physical pianos
βœ…Multiplayer Music Instruction
βœ…PianoVision Music Hall in #VR

More: https://bit.ly/3zYvwGX
❀15🀯6πŸ‘1
This media is not supported in your browser
VIEW IN TELEGRAM
🈯SAMURAI: in-the-wild Shape/Material🈯

πŸ‘‰#Google SAMURAI: shape, BRDF, per-image pose & illumination. Relightable #3D assets for #AR/#VR.

𝐇𝐒𝐠𝐑π₯𝐒𝐠𝐑𝐭𝐬:
βœ…Parametrization for varying distances
βœ…Camera multiplex optimization
βœ…Posterior scaling of input images
βœ…Explicit meshes extraction with BRDF
βœ…Code/data soon available ->#NeurIPS

More: https://bit.ly/3BKWgf3
πŸ‘8πŸ”₯1
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ¦™LaMAR: Localization/Mapping for #ARπŸ¦™

πŸ‘‰A new benchmark for #AR in large and unconstrained scenes

😎Review https://bit.ly/3DjlnWU
😎Paper lamar.ethz.ch/files/LaMAR.pdf
😎Project https://lamar.ethz.ch/
😎Code github.com/microsoft/lamar-benchmark
πŸ‘7πŸ”₯4πŸ’―4
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ‘‘ OnePose++: One-Shot Pose πŸ‘‘

πŸ‘‰Open-source (insane) keypoint-free pose pipeline for #AR

😎Review https://bit.ly/3kF0BdG
😎Paper arxiv.org/pdf/2301.07673.pdf
😎Project zju3dv.github.io/onepose_plus_plus
😎Code github.com/zju3dv/OnePose_Plus_Plus
😎Dataset zjueducn-my.sharepoint.com/personal/12121064_zju_edu_cn/_layouts/15/onedrive.aspx
🀯11πŸ‘9❀1πŸ”₯1
This media is not supported in your browser
VIEW IN TELEGRAM
🧱 MobileBrick: #3D object on mobile 🧱

πŸ‘‰#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
πŸ”₯6πŸ‘2😱1