AI with Papers - Artificial Intelligence & Deep Learning
15K subscribers
95 photos
235 videos
11 files
1.26K links
All the AI with papers. Every day fresh updates on Deep Learning, Machine Learning, and Computer Vision (with Papers).

Curated by Alessandro Ferrari | https://www.linkedin.com/in/visionarynet/
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ“ฏModeling the Human Pose Manifolds๐Ÿ“ฏ

๐Ÿ‘‰#Meta Pose-NDF: continuous model for plausible human poses based on neural distance fields

๐Ÿ˜ŽReview https://bit.ly/3f6X59o
๐Ÿ˜ŽPaper arxiv.org/pdf/2207.13807.pdf
๐Ÿ˜ŽProject virtualhumans.mpi-inf.mpg.de/posendf
๐Ÿ˜ŽCode github.com/garvita-tiwari/PoseNDF
โค6๐Ÿคฏ4
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ’“ Gesture Recognition in 80's ๐Ÿ’“

๐Ÿ‘‰The #Casio AT-550 was offering the edge gesture recognition in 1984!

๐Ÿ˜ŽReview https://bit.ly/3fcPia6
๐Ÿ˜ŽClip: youtube.com/watch?v=piFaJmYpQfQ
๐Ÿคฏ15๐Ÿฅฐ6๐Ÿ”ฅ2
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸŽธMUSIKA! Neural โˆž-audio generation๐ŸŽธ

๐Ÿ‘‰Novel neural music generation system on single consumer GPU!

๐Ÿ˜ŽListen: https://bit.ly/3W80p4U
๐Ÿ˜ŽPaper arxiv.org/pdf/2208.08706.pdf
๐Ÿ˜ŽCode github.com/marcoppasini/musika
๐Ÿคฏ8
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸŒจ๏ธMulti NeRF-supervised Depth-Pose๐ŸŒจ๏ธ

๐Ÿ‘‰NeRF-supervised disentanglement of depth/camera pose from large-scale clips

๐Ÿ˜ŽReview https://bit.ly/3gS4Z7e
๐Ÿ˜ŽPaper arxiv.org/pdf/2210.07181.pdf
๐Ÿ˜ŽProject oasisyang.github.io/self-mpinerf
๐Ÿ˜ฑ4
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸŸง PlanT: Driving Plan w/ Transformer ๐ŸŸง

๐Ÿ‘‰PlanT: planning via transformer. Imitation learning with compact object-level representation

๐Ÿ˜ŽReview https://bit.ly/3Ni2MxN
๐Ÿ˜ŽProject www.katrinrenz.de/plant/
๐Ÿ˜ŽPaper arxiv.org/pdf/2210.14222.pdf
๐Ÿ˜ŽCode github.com/autonomousvision/plant
๐Ÿ”ฅ6๐Ÿ‘2
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ”ฅNetwork -> C++ Converter. Pure Fire!๐Ÿ”ฅ

๐Ÿ‘‰Fully open source #Python framework to convert Neural Nets into C++. Lightning-fast inference๐Ÿ’ฅ

๐Ÿ˜ŽReview https://bit.ly/3gSyqWI
๐Ÿ˜ŽCode github.com/facebookincubator/AITemplate
โค21๐Ÿคฏ12๐Ÿ‘3
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ’ฅTAVA for photo-realistic Avatars๐Ÿ’ฅ

๐Ÿ‘‰#META unveils a novel approach for Template-free Animatable Volumetric Avatars. #Metaverse ready.

๐Ÿ˜ŽReview https://bit.ly/3DPDEvm
๐Ÿ˜ŽPaper arxiv.org/pdf/2206.08929.pdf
๐Ÿ˜ŽProject www.liruilong.cn/projects/tava/
๐Ÿ˜ŽCode github.com/facebookresearch/tava
๐Ÿฅฐ8๐Ÿ‘1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ€ DANNCE: animal keypoints tracking ๐Ÿ€

๐Ÿ‘‰DANNCE: anatomical #3D tracking across species and behaviors

๐Ÿ˜ŽReview https://bit.ly/3Nrx0P3
๐Ÿ˜ŽCode https://github.com/spoonsso/dannce
๐Ÿ”ฅ9๐Ÿ‘6
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸฅปMulti-Garment Virtual Try On (VTON)๐Ÿฅป

๐Ÿ‘‰URJC unveils ULNeFs, a novel approach to efficiently solve mix-and-match VTO for multiple garment layers. SUIT UP!

๐Ÿ˜ŽReview https://bit.ly/3sVVAOC
๐Ÿ˜ŽProject mslab.es/projects/ULNeF
๐Ÿ‘7โค4
โš ๏ธ #AI art is making creatives obsolete โš ๏ธ

1. Scientist: "AI, let's make creatives obsolete"
2. AI: "Ok, let's do it! We have a deal"

๐Ÿ‘‰ The AI ๐Ÿ‘†

๐Ÿ˜ŽMore https://bit.ly/3DBWXa2
๐Ÿคฃ17
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿฉณ STC: Transformers MOT ๐Ÿฉณ

๐Ÿ‘‰A novel Multi-Object Tracking based on Transformers with Dense Representations

๐Ÿ˜ŽReview https://bit.ly/3WzQsNB
๐Ÿ˜ŽPaper arxiv.org/pdf/2210.13570.pdf
๐Ÿ˜ŽCode github.com/amitgalor18/STC_Tracker
๐Ÿคฏ16๐Ÿ‘2
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ”ฅ#AIwithPapers: we are 4,700!๐Ÿ”ฅ

๐Ÿ˜Ž Me, literally, every day ๐Ÿ‘†

๐Ÿ˜ˆ Share -> https://bit.ly/3fA5geu
๐Ÿ˜ˆ Invite friends -> https://t.me/AI_DeepLearning
๐Ÿคฃ29๐Ÿ‘8โค3๐Ÿ”ฅ2โšก1๐Ÿคฉ1๐Ÿพ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ”First Depth/anti-FacRec Cam ๐Ÿ”

๐Ÿ‘‰First working prototype that enables passive depth estimation while inhibiting face identification

๐Ÿ˜ŽCode (coming)
๐Ÿ˜ŽProject https://zaidtas.github.io/privacymask
๐Ÿ˜ŽPaper zaidtas.github.io/privacymask/pdf/privacy_preserving_depth_estimation.pdf
๐Ÿ”ฅ5๐Ÿ‘2๐Ÿคฉ2
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ˜ˆ Synthetic Expression-Wrinkles ๐Ÿ˜ˆ

๐Ÿ‘‰#Microsoft unveils a novel approach that produces realistic wrinkles across humans

๐Ÿ˜ŽReview https://bit.ly/3zWZLOd
๐Ÿ˜ŽPaper arxiv.org/pdf/2210.03529.pdf
๐Ÿ˜ŽProject microsoft.github.io/DynamicWrinkles
๐Ÿ”ฅ7๐Ÿคฏ4๐Ÿ‘2๐Ÿ˜ฑ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ›FactorMatte Video re-Composition๐Ÿ›

๐Ÿ‘‰FactorMatte: alternative formulation of video matting problem for re-composition

๐Ÿ˜ŽReview https://bit.ly/3NX6hdg
๐Ÿ˜ŽPaper arxiv.org/pdf/2211.02145.pdf
๐Ÿ˜ŽProject https://factormatte.github.io/
๐Ÿ˜ŽCode github.com/jacklyngu/FactorMatte
๐Ÿคฏ9๐Ÿ”ฅ7
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ‰ Unifying Flow, Stereo & Depth ๐Ÿ‰

๐Ÿ‘‰A unified neural model for motion and #3D perception tasks

๐Ÿ˜ŽReview https://bit.ly/3AbdnFk
๐Ÿ˜ŽPaper arxiv.org/pdf/2211.05783.pdf
๐Ÿ˜ŽProject haofeixu.github.io/unimatch/
๐Ÿ˜ŽCode github.com/autonomousvision/unimatch
๐Ÿ‘11โšก2
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ”ซ Real-Time Auto Neural Mapping ๐Ÿ”ซ

๐Ÿ‘‰Robot can densely annotate a scene via fully-autonomous experimental interactions

๐Ÿ˜ŽReview https://bit.ly/3GfwQbY
๐Ÿ˜ŽPaper arxiv.org/pdf/2210.17325.pdf
๐Ÿ˜ŽProject ihaughton.github.io/RobE
๐Ÿ”ฅ8โšก2
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ”๏ธ InfiniteNature-Zero: โˆž Video ๐Ÿ”๏ธ

๐Ÿ‘‰Open-source generative #AI for unbounded flythrough videos of natural scenes

๐Ÿ˜ŽReview https://bit.ly/3hJYELa
๐Ÿ˜ŽPaper arxiv.org/pdf/2207.11148.pdf
๐Ÿ˜ŽProject infinite-nature-zero.github.io
๐Ÿ˜ŽCode https://github.com/google-research/google-research/tree/master/infinite_nature_zero
โค12๐Ÿ‘4๐Ÿ”ฅ2โšก1๐Ÿฅฐ1๐Ÿ‘1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸงถOpen-Source Neural Inpainting Suite๐Ÿงถ

๐Ÿ‘‰Lama Cleaner: a free and open-source inpainting tool powered by SOTA #AI model

๐Ÿ˜ŽReview https://bit.ly/3Ex2aSq
๐Ÿ˜ŽProject github.com/Sanster/lama-cleaner
๐Ÿคฏ12๐Ÿพ2๐Ÿฅฐ1