AI with Papers - Artificial Intelligence & Deep Learning
15K subscribers
95 photos
237 videos
11 files
1.27K 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”ฅ๐Ÿ”ฅMagicVideo: Text-To-Video #AI๐Ÿ”ฅ๐Ÿ”ฅ

๐Ÿ‘‰MagicVideo: novel efficient text-to-video AI based on latent diffusion models

๐Ÿ˜ŽReview https://bit.ly/3UX5YCd
๐Ÿ˜ŽPaper arxiv.org/pdf/2211.11018.pdf
๐Ÿ˜ŽProject magicvideo.github.io/
๐Ÿ˜ฑ8๐Ÿ‘2๐Ÿ’ฉ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸงŸโ€โ™€๏ธ Generative Neural Texture for Avatars ๐ŸงŸโ€โ™€๏ธ

๐Ÿ‘‰Novel #3D GAN for (the most, ever) detailed facial avatars from unstructured 2D images

๐Ÿ˜ŽReview https://bit.ly/3EvF0dS
๐Ÿ˜ŽProject mrtornado24.github.io/Next3D/
๐Ÿ˜ŽPaper arxiv.org/pdf/2211.11208.pdf
๐Ÿ˜ŽCode github.com/MrTornado24/Next3D
๐Ÿ”ฅ6๐Ÿ˜ฑ4๐Ÿ‘2
๐Ÿ”ฅ๐Ÿ”ฅ "There can be only one" ๐Ÿ”ฅ๐Ÿ”ฅ

๐Ÿ‘‰#Catfighting from the #AI community ๐Ÿ˜‚

๐Ÿ˜ŽReview https://bit.ly/3Ax5I4n
๐Ÿคฃ7๐Ÿ‘5๐Ÿพ2
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ–Œ๏ธ Neural Semantic Image Synthesis ๐Ÿ–Œ๏ธ

๐Ÿ‘‰Adobe unveils SceneComposer: text to 2D semantic canvas with precise shapes

๐Ÿ˜ŽReview https://bit.ly/3EtDyIL
๐Ÿ˜ŽProject zengyu.me/scenec
๐Ÿ˜ŽPaper arxiv.org/pdf/2211.11742.pdf
๐Ÿ˜ŽCode github.com/zengxianyu/scenec
๐Ÿคฏ10โค4โšก1๐Ÿ‘1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿน Perceptual NeRF-Inpainting ๐Ÿน

๐Ÿ‘‰A novel complete process for #3D scene manipulation powered by NeRF

๐Ÿ˜ŽReview https://bit.ly/3Vn0EaT
๐Ÿ˜ŽPaper arxiv.org/pdf/2211.12254.pdf
๐Ÿ˜ŽProject spinnerf3d.github.io
๐Ÿ‘5๐Ÿ”ฅ3๐Ÿพ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ”ฅ Stable Diffusion 2.0 is out! ๐Ÿ”ฅ

๐Ÿ‘‰The open-source of #StableDiffusion V2 just released. Magic ๐Ÿคฏ

๐Ÿ˜ŽReview https://bit.ly/3XwGInO
๐Ÿ˜ŽCode github.com/Stability-AI/stablediffusion
๐Ÿ˜ŽBlog stability.ai/blog/stable-diffusion-v2-release
๐Ÿคฏ17๐Ÿ‘8๐Ÿพ4โšก3๐Ÿ˜ฑ3๐Ÿ˜1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿฅ‡MineDojo: Agents at Internet-Scale๐Ÿฅ‡

๐Ÿ‘‰The #neurips2022 Outstanding Paper Award winner is out. By #Nvidia et al.

๐Ÿ˜ŽReview https://bit.ly/3F0RPhN
๐Ÿ˜ŽProject https://minedojo.org/
๐Ÿ˜ŽPaper arxiv.org/pdf/2206.08853.pdf
๐Ÿ˜ŽCode github.com/MineDojo/MineDojo
๐Ÿ”ฅ10๐Ÿคฉ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿซ Tracking in Motion-Blurred Clips ๐Ÿซ

๐Ÿ‘‰Robust line segment detector in motion-blurred clips -> #SLAM / #3D.

๐Ÿ˜ŽReview https://bit.ly/3F2wHrb
๐Ÿ˜ŽPaper arxiv.org/pdf/2211.07365.pdf
๐Ÿ˜ŽProject levenberg.github.io/FE-LSD/
๐Ÿ˜ŽCode github.com/lh9171338/FE-LSD
๐Ÿคฏ5๐Ÿ‘2๐Ÿ”ฅ2โšก1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ’ƒEDGE: Diffusive Dancers Generator๐Ÿ’ƒ

๐Ÿ‘‰New SOTA in editable human-dancer generation according to the input music

๐Ÿ˜ŽReview https://bit.ly/3u2egfY
๐Ÿ˜ŽPaper arxiv.org/pdf/2211.10658.pdf
๐Ÿ˜ŽProject edge-dance.github.io/
โค8๐Ÿคฉ2๐Ÿคฏ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿฅฌ Diffusive Sketch-Guided Text-to-Image ๐Ÿฅฌ

๐Ÿ‘‰#Google unveils a universal approach for T2I (pre-trained) diffusion: free-hand, saliency-guided, etc.

๐Ÿ˜ŽReview https://bit.ly/3XFVMj2
๐Ÿ˜ŽProject sketch-guided-diffusion.github.io/
๐Ÿ˜ŽPaper sketch-guided-diffusion.github.io/files/sketch-guided-preprint.pdf
๐Ÿคฏ4โšก1โค1๐Ÿ‘1๐Ÿ”ฅ1๐Ÿฅฐ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿˆ SpaText: Spatio-Textual Generation ๐Ÿˆ

๐Ÿ‘‰#META AI unveils a novel T2I using open-vocabulary scene control

๐Ÿ˜ŽReview https://bit.ly/3OKcdXz
๐Ÿ˜ŽProject omriavrahami.com/spatext/
๐Ÿ˜ŽPaper arxiv.org/pdf/2211.14305.pdf
๐Ÿ˜ŽCode (coming)
๐Ÿคฏ7๐Ÿ˜ฑ2โค1๐Ÿ”ฅ1๐Ÿคฉ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ’กDiffusive Generation/Inpainting/Reconstruction๐Ÿ’ก

๐Ÿ‘‰The first 3D-aware diffusion model purely trained from 2D images only

๐Ÿ˜ŽReview https://bit.ly/3XyHyjY
๐Ÿ˜ŽPaper arxiv.org/pdf/2211.09869.pdf
๐Ÿ˜ŽCode github.com/Anciukevicius/RenderDiffusion
โค5๐Ÿ‘2๐Ÿ”ฅ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿš— 3DDesigner: Text-guided Diffusion ๐Ÿš—

๐Ÿ‘‰Novel method to generate #3D fine-grained objects via textual diffusion

๐Ÿ˜ŽReview https://bit.ly/3Fbmyc1
๐Ÿ˜ŽProject 3ddesigner-diffusion.github.io/
๐Ÿ˜ŽPaper arxiv.org/pdf/2211.14108.pdf
๐Ÿ”ฅ8๐Ÿ‘2๐Ÿคฏ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸงจFast-SNARF: 150ร— faster NeRF๐Ÿงจ

๐Ÿ‘‰Voxel-based, pre-computed skinning, #cuda kernels -> avatar 150x faster!

๐Ÿ˜ŽReview https://bit.ly/3OMvEPo
๐Ÿ˜ŽCode github.com/xuchen-ethz/fast-snarf
๐Ÿ˜ŽPaper dataset.ait.ethz.ch/downloads/fast-snarf/paper.pdf
๐Ÿ”ฅ7๐Ÿคฉ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ”ฅ#AIwithPapers: we are 5,200+!๐Ÿ”ฅ

๐Ÿ‘‰ Me (and you, all), these days (audio ON)๐Ÿคฃ

๐Ÿ˜ˆ Share -> https://bit.ly/3VBGN7Y
๐Ÿ˜ˆ Invite friends -> https://t.me/AI_DeepLearning
๐Ÿฅฐ7๐Ÿคฃ5๐Ÿคฉ2๐Ÿ˜ฑ1
๐Ÿ”ฅ๐Ÿ”ฅ Distilled #StableDiffusion paper! ๐Ÿ”ฅ๐Ÿ”ฅ

๐Ÿ‘‰The progress with #StableDiffusion at #neurips2022 conference. Crazy times!

๐Ÿ˜ŽReview https://bit.ly/3ESo5Cn
๐Ÿ˜ŽPaper arxiv.org/pdf/2210.03142.pdf
๐Ÿ‘18๐Ÿคฏ3๐Ÿ”ฅ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ’Ž SJC: from 2D -> #3D generation ๐Ÿ’Ž

๐Ÿ‘‰ Novel method to convert pretrained 2D diffusion into 3D generative mode

๐Ÿ˜ŽReview https://bit.ly/3UppHJx
๐Ÿ˜ŽPaper arxiv.org/pdf/2212.00774.pdf
๐Ÿ˜ŽCode github.com/pals-ttic/sjc
๐Ÿ˜ŽProject pals.ttic.edu/p/score-jacobian-chaining
โค2โšก2๐Ÿ‘1๐Ÿ”ฅ1๐Ÿคฉ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿคช Just another ORDINARY week in #AI community ๐Ÿคช

๐Ÿ˜ˆ Let's talk -> https://bit.ly/3VsEfth
๐Ÿ˜ˆ Invite friends -> https://t.me/AI_DeepLearning
๐Ÿคฃ10๐Ÿ‘1๐Ÿ”ฅ1