AI with Papers - Artificial Intelligence & Deep Learning
15.2K subscribers
135 photos
247 videos
14 files
1.31K 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
Hello everybody,
a lot of you asked me to re-open the sharing of the contents to involve more people. I want to follow your suggestion, hope you will enjoy this new mood!

👍 FREE TO FORWARD TO OTHER TELEGRAM CHANNELS

đŸ”Ĩ NO COPY OF THE POSTS
đŸ”Ĩ NO COMMERCIAL USAGE
đŸ”Ĩ NO UNRESPECTFUL USAGE

âš ī¸ UNDO THE FORWARDING OPTION AT THE FIRST VIOLATION âš ī¸
❤19👍10👏3đŸĨ°1🍾1
This media is not supported in your browser
VIEW IN TELEGRAM
🩰 Magic Animating Human 🩰

👉MagicAnimate: the new SOTA in human animation. Code available: let's dance!

👉Review https://t.ly/Oq7Za
👉Paper https://lnkd.in/dSUbGgCs
👉Project https://lnkd.in/dkVFf-SV
👉Code https://lnkd.in/dj2dbzdg
👉Demo https://lnkd.in/dHEKPE9q
đŸ¤¯6❤2👍1đŸ”Ĩ1đŸĨ°1
This media is not supported in your browser
VIEW IN TELEGRAM
đŸ”Ĩ EfficientSAM: 20x faster Segment Anything đŸ”Ĩ

👉Meta AI Research unveils a novel family of SAM-like models, light-weight SAM models with SOTA quality-efficiency trade-offs. Up to 20x faster!

👉Review https://t.ly/966QS
👉Paper https://lnkd.in/duijp_Rh
👉Project https://lnkd.in/dW-p2CuH
👉Code https://lnkd.in/dAbZaB2t
👉Demo https://lnkd.in/d-tjKiUd
đŸ”Ĩ15❤4👍4đŸ¤¯2
This media is not supported in your browser
VIEW IN TELEGRAM
đŸĢļ3D Hands with TransformersđŸĢļ

👉 HaMeR is a robust and accurate Hand Mesh Recovery from images and video frames, based on Transformer architecture. It's the new SOTA.

👉Review https://t.ly/YtAW8
👉Paper https://arxiv.org/pdf/2312.05251.pdf
👉Project https://geopavlakos.github.io/hamer
👉Demo huggingface.co/spaces/geopavlakos/HaMeR
👉Colab colab.research.google.com/drive/1rQbQzegFWGVOm1n1d-S6koOWDo7F2ucu
👍10❤1👏1đŸ¤¯1😱1
This media is not supported in your browser
VIEW IN TELEGRAM
đŸĒŠ DreaMoving: Human Dancer đŸĒŠ

👉Alibaba strikes again with DreaMoving: a diffusion-based controllable video generation framework to produce HQ customized human videos.

👉Review https://t.ly/BD_Yf
👉Paper https://lnkd.in/gepP6Rjw
👉Project https://lnkd.in/gwm72cfS
👉Repo (empty) https://lnkd.in/gsc2Qt-F
👍7💩6❤2đŸĨ°1
This media is not supported in your browser
VIEW IN TELEGRAM
📲 EdgeSAM: Mobile 40x SAM 📲

👉A novel hyper-optimized version of SAM for mobile devices such as #Iphone. Pure CNNs backbone (better suitable for ANE), up to 40x faster. Code available 😉

👉Review https://t.ly/m_vLH
👉Paper https://lnkd.in/gHZVZN2x
👉Project https://lnkd.in/gK8qEK8p
👉Repo https://lnkd.in/gj6YAGNv
👉Hugging Face https://lnkd.in/gUUHJvxz
đŸ”Ĩ20⚡2❤2🤩1
This media is not supported in your browser
VIEW IN TELEGRAM
đŸĒŧPatchFusion: SOTA Mono-DepthđŸĒŧ

👉PatchFusion: novel end-to-end tile-based framework for hi-res monocular metric depth estimation. It's the new SOTA in metric depth estimation from mono. Code & Demo on Hugging Face able đŸ”Ĩ

👉Review https://t.ly/hv3yT
👉Paper https://lnkd.in/d9dXP7iP
👉Project https://lnkd.in/dQcvVJSx
👉Repo https://lnkd.in/dW2GdVR5
👉Demo https://lnkd.in/dFW-gAiY
đŸ”Ĩ10❤5👏1đŸ¤¯1😱1
This media is not supported in your browser
VIEW IN TELEGRAM
💃Outfit Anyone: Ultra-HQ VTO💃

👉Alibaba unveils Outfit Anyone: a two-stream conditional diffusion able to adeptly handle garment deformation for more lifelike results in VOT. Extra: Outfit Anyone + Animate Anyone for outfit + motion generation of any character. NO CODE / NO PAPER / DEMO AVAILABLE :)

👉Review https://t.ly/o6UR9
👉Demo https://lnkd.in/dpQYdXhc
👉Repo (empty) https://lnkd.in/dBsNST6r
đŸ¤¯10👍4❤3đŸ”Ĩ2
đŸ”Ĩ #AIwithPapers: we are 8k+ đŸ”Ĩ

👉 After flirting with #ChatGpt for months, you back in love with this channel. I felt bad, but I forgive you 🧡

😈 Hey Telegram Premium Subscribers, what about boosting us? Click: https://t.iss.one/AI_DeepLearning?boost

😈 Invite -> https://t.iss.one/AI_DeepLearning
❤16đŸ¤Ŗ7đŸ”Ĩ1đŸĨ°1
This media is not supported in your browser
VIEW IN TELEGRAM
🧊 Depth Conditioning 🧊

👉LooseControl to control the generative image modeling process. Layout by boundaries and #3D box control via object locations (approximate bounding boxes)

👉Review https://t.ly/9y72m
👉Paper https://arxiv.org/pdf/2312.03079.pdf
👉Project https://shariqfarooq123.github.io/loose-control/
👉Repo https://github.com/shariqfarooq123/LooseControl
đŸ”Ĩ14❤6đŸ¤¯4👍1đŸĨ°1
This media is not supported in your browser
VIEW IN TELEGRAM
đŸ–˛ī¸ Amodal Tracking Any Object đŸ–˛ī¸

👉Amodal tracking": inferring complete object boundaries, even when certain portions are occluded. New benchmark & approach, 2x better than SOTA in people tracking đŸ”Ĩ

👉Review https://t.ly/Rc6Ku
👉Paper https://lnkd.in/d39rFYT4
👉Project https://lnkd.in/d7bkEcni
👉(empty) Repo https://lnkd.in/dTsNKdfz
❤16đŸ¤¯8đŸ”Ĩ3👍2👏1😱1
This media is not supported in your browser
VIEW IN TELEGRAM
đŸšŋ Event-Cam (1000 fps) Hands đŸšŋ

👉Ev2Hands, the first method for the 3D reconstruction of two interacting hands from a single event camera. Code available.

👉Review https://t.ly/YpQpX
👉Paper arxiv.org/pdf/2312.14157.pdf
👉Project 4dqv.mpi-inf.mpg.de/Ev2Hands
👉Repo github.com/Chris10M/Ev2Hands
đŸ”Ĩ3❤2👍2👏1
This media is not supported in your browser
VIEW IN TELEGRAM
🎄UniSDF: Unifying Neural Representations🎄

👉UniSDF: novel general purpose 3D reconstruction for large complex scenes with reflections. SOTA on DTU, Shiny Blender, Mip-NeRF 360 and Ref-NeRF dataset.

👉Review https://t.ly/2QEul
👉Paper https://arxiv.org/pdf/2312.13285.pdf
👉Project https://fangjinhuawang.github.io/UniSDF/
👉Repo: No code :(
đŸ”Ĩ7👍2❤1đŸĨ°1đŸ¤¯1
This media is not supported in your browser
VIEW IN TELEGRAM
đŸĒŽHAAR: Text-Driven Generative HairstylesđŸĒŽ

👉 HAAR: new strand-based generative model for #3D human hairstyles driven by textual input.

👉Review https://t.ly/L38iD
👉Project https://haar.is.tue.mpg.de/
👉Paper https://arxiv.org/pdf/2312.11666.pdf
👉Repo coming
đŸ¤¯4🍾3👍2đŸ”Ĩ1
This media is not supported in your browser
VIEW IN TELEGRAM
đŸĒ˛UniRef++: Segment Every ReferenceđŸĒ˛

👉 UniRef++ is a unified model for RIS, FSS, RVOS & VOS. Code available!

👉Review https://t.ly/OxtOx
👉Paper https://lnkd.in/eTrmDTK3
👉Repo https://lnkd.in/etfTm4Wq
👍11❤3đŸ¤¯3⚡1
This media is not supported in your browser
VIEW IN TELEGRAM
🈚 Seeing Through Occlusions 🈚

👉Novel NSF to see through occlusions, reflection suppression & shadow removal.

👉Review https://t.ly/5jcIG
👉Project https://light.princeton.edu/publication/nsf
👉Paper https://arxiv.org/pdf/2312.14235.pdf
👉Repo https://github.com/princeton-computational-imaging/NSF
❤10đŸ¤¯7đŸ”Ĩ3🍾1
This media is not supported in your browser
VIEW IN TELEGRAM
đŸ‘ģ Avatar Behind Occlusions đŸ‘ģ

👉Neural rendering for occluded in-the-wild mono-videos. Decoupling scenes in occlusion, human, and background.

👉Review https://t.ly/8q__B
👉Paper https://arxiv.org/pdf/2401.00431.pdf
👉Project https://cs.stanford.edu/~xtiange/projects/wild2avatar
đŸ”Ĩ11❤3👏1🤩1
This media is not supported in your browser
VIEW IN TELEGRAM
🕍 En3D: Generative 3D Humans 🕍

👉#Alibaba unveils En3D: generative scheme for sculpting HQ 3D human avatars. Zero-shot 3D generative scheme capable of producing visually realistic, geometrically accurate and content-wise diverse 3D humans without relying on pre-existing 3D or 2D asset.

👉Review https://t.ly/nGmDK
👉Project menyifang.github.io/projects/En3D/index.html
👉Paper https://arxiv.org/pdf/2401.01173.pdf
👉Repo (soon?) https://github.com/menyifang/En3D
đŸ¤¯5❤3đŸ”Ĩ1
This media is not supported in your browser
VIEW IN TELEGRAM
🐤 MagicVideo-V2 announced! 🐤

👉#Bytedance announces a novel multi-stage pipeline capable of generating high-aesthetic videos from textual description

👉Review https://t.ly/zIq4v
👉Project https://lnkd.in/dKUrJPJd
👉Paper https://lnkd.in/dixnN-kU
đŸ”Ĩ7❤1👍1đŸĨ°1💩1
This media is not supported in your browser
VIEW IN TELEGRAM
đŸ”Ĩ #6D Foundation Pose đŸ”Ĩ

👉#Nvidia unveils FoundationPose, a novel (and unified) foundation model for 6D object pose estimation and tracking.

👉Review https://t.ly/HGd4h
👉Project https://lnkd.in/dPcnBKWm
👉Paper https://lnkd.in/dixn_iHZ
👉Code coming 🩷
đŸ”Ĩ12❤5👏1đŸ¤¯1
🃏ReplaceAnything: demo is out!🃏

👉ReplaceAnything: ultra-high quality content replacement. The ultimate #AI solution for human, clothing & background replacement to change the e-commerce experience for vendors.

👉Review https://t.ly/FMyvf
👉Project https://lnkd.in/dcyZvP2b
👉ModelScope https://lnkd.in/dU4x4nE6
👉Hugging Face https://lnkd.in/dn3uXWgd
👉Empty report https://lnkd.in/dcuGXd6c
👉Paper coming?
❤11👍3👏2😍1