AI with Papers - Artificial Intelligence & Deep Learning
🎷 Pix2Seq: object detection by #Google 🎷 👉A novel framework to perform object detection as a language modeling task 𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬: ✅Obj. detection as a lang-modeling task ✅BBs/labels -> seq. of discrete token ✅Encoder-decoder (one token at a time) ✅Code under…
This media is not supported in your browser
VIEW IN TELEGRAM
⚡4🥰2👍1😱1
This media is not supported in your browser
VIEW IN TELEGRAM
🍫 Tracking in Motion-Blurred Clips 🍫
👉Robust line segment detector in motion-blurred clips -> #SLAM / #3D.
😎Review https://bit.ly/3F2wHrb
😎Paper arxiv.org/pdf/2211.07365.pdf
😎Project levenberg.github.io/FE-LSD/
😎Code github.com/lh9171338/FE-LSD
👉Robust line segment detector in motion-blurred clips -> #SLAM / #3D.
😎Review https://bit.ly/3F2wHrb
😎Paper arxiv.org/pdf/2211.07365.pdf
😎Project levenberg.github.io/FE-LSD/
😎Code github.com/lh9171338/FE-LSD
🤯5👍2🔥2⚡1
This media is not supported in your browser
VIEW IN TELEGRAM
💃EDGE: Diffusive Dancers Generator💃
👉New SOTA in editable human-dancer generation according to the input music
😎Review https://bit.ly/3u2egfY
😎Paper arxiv.org/pdf/2211.10658.pdf
😎Project edge-dance.github.io/
👉New SOTA in editable human-dancer generation according to the input music
😎Review https://bit.ly/3u2egfY
😎Paper arxiv.org/pdf/2211.10658.pdf
😎Project edge-dance.github.io/
❤8🤩2🤯1
This media is not supported in your browser
VIEW IN TELEGRAM
🥬 Diffusive Sketch-Guided Text-to-Image 🥬
👉#Google unveils a universal approach for T2I (pre-trained) diffusion: free-hand, saliency-guided, etc.
😎Review https://bit.ly/3XFVMj2
😎Project sketch-guided-diffusion.github.io/
😎Paper sketch-guided-diffusion.github.io/files/sketch-guided-preprint.pdf
👉#Google unveils a universal approach for T2I (pre-trained) diffusion: free-hand, saliency-guided, etc.
😎Review https://bit.ly/3XFVMj2
😎Project sketch-guided-diffusion.github.io/
😎Paper sketch-guided-diffusion.github.io/files/sketch-guided-preprint.pdf
🤯4⚡1❤1👍1🔥1🥰1
This media is not supported in your browser
VIEW IN TELEGRAM
🐈 SpaText: Spatio-Textual Generation 🐈
👉#META AI unveils a novel T2I using open-vocabulary scene control
😎Review https://bit.ly/3OKcdXz
😎Project omriavrahami.com/spatext/
😎Paper arxiv.org/pdf/2211.14305.pdf
😎Code (coming)
👉#META AI unveils a novel T2I using open-vocabulary scene control
😎Review https://bit.ly/3OKcdXz
😎Project omriavrahami.com/spatext/
😎Paper arxiv.org/pdf/2211.14305.pdf
😎Code (coming)
🤯7😱2❤1🔥1🤩1
This media is not supported in your browser
VIEW IN TELEGRAM
💡Diffusive Generation/Inpainting/Reconstruction💡
👉The first 3D-aware diffusion model purely trained from 2D images only
😎Review https://bit.ly/3XyHyjY
😎Paper arxiv.org/pdf/2211.09869.pdf
😎Code github.com/Anciukevicius/RenderDiffusion
👉The first 3D-aware diffusion model purely trained from 2D images only
😎Review https://bit.ly/3XyHyjY
😎Paper arxiv.org/pdf/2211.09869.pdf
😎Code github.com/Anciukevicius/RenderDiffusion
❤5👍2🔥1
This media is not supported in your browser
VIEW IN TELEGRAM
🚗 3DDesigner: Text-guided Diffusion 🚗
👉Novel method to generate #3D fine-grained objects via textual diffusion
😎Review https://bit.ly/3Fbmyc1
😎Project 3ddesigner-diffusion.github.io/
😎Paper arxiv.org/pdf/2211.14108.pdf
👉Novel method to generate #3D fine-grained objects via textual diffusion
😎Review https://bit.ly/3Fbmyc1
😎Project 3ddesigner-diffusion.github.io/
😎Paper arxiv.org/pdf/2211.14108.pdf
🔥8👍2🤯1
This media is not supported in your browser
VIEW IN TELEGRAM
🧨Fast-SNARF: 150× faster NeRF🧨
👉Voxel-based, pre-computed skinning, #cuda kernels -> avatar 150x faster!
😎Review https://bit.ly/3OMvEPo
😎Code github.com/xuchen-ethz/fast-snarf
😎Paper dataset.ait.ethz.ch/downloads/fast-snarf/paper.pdf
👉Voxel-based, pre-computed skinning, #cuda kernels -> avatar 150x faster!
😎Review https://bit.ly/3OMvEPo
😎Code github.com/xuchen-ethz/fast-snarf
😎Paper dataset.ait.ethz.ch/downloads/fast-snarf/paper.pdf
🔥7🤩1
This media is not supported in your browser
VIEW IN TELEGRAM
🔥#AIwithPapers: we are 5,200+!🔥
👉 Me (and you, all), these days (audio ON)🤣
😈 Share -> https://bit.ly/3VBGN7Y
😈 Invite friends -> https://news.1rj.ru/str/AI_DeepLearning
👉 Me (and you, all), these days (audio ON)🤣
😈 Share -> https://bit.ly/3VBGN7Y
😈 Invite friends -> https://news.1rj.ru/str/AI_DeepLearning
🥰7🤣5🤩2😱1
🔥🔥 Distilled #StableDiffusion paper! 🔥🔥
👉The progress with #StableDiffusion at #neurips2022 conference. Crazy times!
😎Review https://bit.ly/3ESo5Cn
😎Paper arxiv.org/pdf/2210.03142.pdf
👉The progress with #StableDiffusion at #neurips2022 conference. Crazy times!
😎Review https://bit.ly/3ESo5Cn
😎Paper arxiv.org/pdf/2210.03142.pdf
👍18🤯3🔥1
This media is not supported in your browser
VIEW IN TELEGRAM
💎 SJC: from 2D -> #3D generation 💎
👉 Novel method to convert pretrained 2D diffusion into 3D generative mode
😎Review https://bit.ly/3UppHJx
😎Paper arxiv.org/pdf/2212.00774.pdf
😎Code github.com/pals-ttic/sjc
😎Project pals.ttic.edu/p/score-jacobian-chaining
👉 Novel method to convert pretrained 2D diffusion into 3D generative mode
😎Review https://bit.ly/3UppHJx
😎Paper arxiv.org/pdf/2212.00774.pdf
😎Code github.com/pals-ttic/sjc
😎Project pals.ttic.edu/p/score-jacobian-chaining
❤2⚡2👍1🔥1🤩1
This media is not supported in your browser
VIEW IN TELEGRAM
🤪 Just another ORDINARY week in #AI community 🤪
😈 Let's talk -> https://bit.ly/3VsEfth
😈 Invite friends -> https://news.1rj.ru/str/AI_DeepLearning
😈 Let's talk -> https://bit.ly/3VsEfth
😈 Invite friends -> https://news.1rj.ru/str/AI_DeepLearning
🤣10👍1🔥1
Should I write a book (no technicalities, for everyone) about the evolution of the modern Computer Vision / AI ?
Anonymous Poll
81%
Yes, please!🧡
19%
No, c'mon. Comment -> https://bit.ly/3B6T6S9
❤9🔥3🥰1
This media is not supported in your browser
VIEW IN TELEGRAM
🎨 Dr.3D: adapting 3D GANs to Arts 🎨
👉Novel 3D GAN domain adaptation method for drawings. From portraits to 3D!
😎Review https://bit.ly/3He3Phv
😎Paper arxiv.org/pdf/2211.16798.pdf
😎Project jinwonjoon.github.io/dr3d/
😎Code github.com/JinWonjoon/Dr.3D
👉Novel 3D GAN domain adaptation method for drawings. From portraits to 3D!
😎Review https://bit.ly/3He3Phv
😎Paper arxiv.org/pdf/2211.16798.pdf
😎Project jinwonjoon.github.io/dr3d/
😎Code github.com/JinWonjoon/Dr.3D
🥰4🔥2⚡1👍1🤯1
This media is not supported in your browser
VIEW IN TELEGRAM
🫐 Tracking EVERYTHING in the wild 🫐
👉Disentangling classification from tracking, Track Every Thing Accuracy (TETA) for SOTA
😎Review https://bit.ly/3F2rfU7
😎Paper arxiv.org/pdf/2207.12978.pdf
😎Project www.vis.xyz/pub/tet/
👉Disentangling classification from tracking, Track Every Thing Accuracy (TETA) for SOTA
😎Review https://bit.ly/3F2rfU7
😎Paper arxiv.org/pdf/2207.12978.pdf
😎Project www.vis.xyz/pub/tet/
🤯4👍1🔥1🤩1
This media is not supported in your browser
VIEW IN TELEGRAM
👽HD Faces via "Hacked" Smartphone👽
👉A novel method for HD faces from (polarizing-foils) smartphones
😎Review https://bit.ly/3H8yhJN
😎Paper arxiv.org/pdf/2212.01160.pdf
😎Project dazinovic.github.io/polface
👉A novel method for HD faces from (polarizing-foils) smartphones
😎Review https://bit.ly/3H8yhJN
😎Paper arxiv.org/pdf/2212.01160.pdf
😎Project dazinovic.github.io/polface
🔥4🤯1😱1
This media is not supported in your browser
VIEW IN TELEGRAM
💎 Clothes-Changing Re-Identification 💎
👉The new SOTA in wild Re-identification by mixing appearance & face features
😎Review https://bit.ly/3HdTTUU
😎Paper arxiv.org/pdf/2211.13807.pdf
😎Project www.vision.huji.ac.il/reface
😎Code github.com/bar371/ReFace
👉The new SOTA in wild Re-identification by mixing appearance & face features
😎Review https://bit.ly/3HdTTUU
😎Paper arxiv.org/pdf/2211.13807.pdf
😎Project www.vision.huji.ac.il/reface
😎Code github.com/bar371/ReFace
👍5🤯3⚡2😱1
This media is not supported in your browser
VIEW IN TELEGRAM
👘 SOTA: One-Shot Animatable Avatars 👘
👉ELICIT: synthesis & avatar animation -> NeRF representation in one-shot
😎Review https://bit.ly/3P3eZY6
😎Paper arxiv.org/pdf/2212.02469.pdf
😎Project https://elicit3d.github.io/
😎Code github.com/huangyangyi/ELICIT
👉ELICIT: synthesis & avatar animation -> NeRF representation in one-shot
😎Review https://bit.ly/3P3eZY6
😎Paper arxiv.org/pdf/2212.02469.pdf
😎Project https://elicit3d.github.io/
😎Code github.com/huangyangyi/ELICIT
🔥4👍2❤1🥰1😱1💩1
This media is not supported in your browser
VIEW IN TELEGRAM
🐸 RANA: Neural Avatar by #Nvidia 🐸
👉Neural humans under arbitrary viewpoints, body poses & lighting
😎Review https://bit.ly/3iIYOTP
😎Paper arxiv.org/pdf/2212.03237.pdf
😎Project nvlabs.github.io/RANA
👉Neural humans under arbitrary viewpoints, body poses & lighting
😎Review https://bit.ly/3iIYOTP
😎Paper arxiv.org/pdf/2212.03237.pdf
😎Project nvlabs.github.io/RANA
🔥7👍3👏1
This media is not supported in your browser
VIEW IN TELEGRAM
🧰UDE: Unified Human Motion Generation🧰
👉The first unified human motion from Text or Audio. Audio ON, New SOTA.
😎Review https://bit.ly/3HjWsVN
😎Paper arxiv.org/pdf/2211.16016.pdf
😎Project zixiangzhou916.github.io/UDE
😎Code github.com/zixiangzhou916/UDE
👉The first unified human motion from Text or Audio. Audio ON, New SOTA.
😎Review https://bit.ly/3HjWsVN
😎Paper arxiv.org/pdf/2211.16016.pdf
😎Project zixiangzhou916.github.io/UDE
😎Code github.com/zixiangzhou916/UDE
👍2🔥2⚡1🤩1