This media is not supported in your browser
VIEW IN TELEGRAM
🔥 E2POSE: code is out! 🔥
👉E2Pose: fully convolutional networks for e2e multi-person pose estimation
😎Review https://bit.ly/3WelGsP
😎Code github.com/AISIN-TRC/E2Pose
😎Tutorial cedro3.com/ai/e2pose/
😎Paper, not yet 🤷♂️
👉E2Pose: fully convolutional networks for e2e multi-person pose estimation
😎Review https://bit.ly/3WelGsP
😎Code github.com/AISIN-TRC/E2Pose
😎Tutorial cedro3.com/ai/e2pose/
😎Paper, not yet 🤷♂️
🔥7⚡2🤯1
This media is not supported in your browser
VIEW IN TELEGRAM
🧙Distortion-Aware Neural Selection 🧙
👉#Adobe unveils a novel method for interactive workflows used for decaling, texturing, or painting on surfaces
😎Review https://bit.ly/3uSou3b
😎Project threedle.github.io/DA-Wand
😎Paper https://drive.google.com/file/d/1OkGwIPQb9RUeT5aw-X_tdBAPG0bB4dNQ/view
👉#Adobe unveils a novel method for interactive workflows used for decaling, texturing, or painting on surfaces
😎Review https://bit.ly/3uSou3b
😎Project threedle.github.io/DA-Wand
😎Paper https://drive.google.com/file/d/1OkGwIPQb9RUeT5aw-X_tdBAPG0bB4dNQ/view
🔥3👍1🤯1
🔥 GhostNetV2: Pure Neural Fire! 🔥
👉 Novel HW-friendly attention & GhostNetV2 for mobile. Top-1 with only 167M FLOPs
😎Review https://bit.ly/3j2EIUJ
😎Paper arxiv.org/pdf/2211.12905.pdf
👉 Novel HW-friendly attention & GhostNetV2 for mobile. Top-1 with only 167M FLOPs
😎Review https://bit.ly/3j2EIUJ
😎Paper arxiv.org/pdf/2211.12905.pdf
🤯4🔥2⚡1
This media is not supported in your browser
VIEW IN TELEGRAM
🧲 MAGVIT: 250x Faster Transformer 🧲
👉MAGVIT: ONE model -> 10+ video synthesis tasks!
😎Review https://bit.ly/3FX2P09
😎Project magvit.cs.cmu.edu/
😎Paper arxiv.org/pdf/2212.05199.pdf
😎Code github.com/MAGVIT/magvit
👉MAGVIT: ONE model -> 10+ video synthesis tasks!
😎Review https://bit.ly/3FX2P09
😎Project magvit.cs.cmu.edu/
😎Paper arxiv.org/pdf/2212.05199.pdf
😎Code github.com/MAGVIT/magvit
🤯9🔥2😱2🤩1
This media is not supported in your browser
VIEW IN TELEGRAM
🎯 MOTRv2: Tracking by Pretrained Model 🎯
👉MOTRv2: e2e multi-object tracking with pretrained detector
😎Review https://bit.ly/3UYzvdN
😎Paper arxiv.org/pdf/2211.09791.pdf
😎Code github.com/megvii-research/MOTRv2
👉MOTRv2: e2e multi-object tracking with pretrained detector
😎Review https://bit.ly/3UYzvdN
😎Paper arxiv.org/pdf/2211.09791.pdf
😎Code github.com/megvii-research/MOTRv2
👍2🔥1🤩1
This media is not supported in your browser
VIEW IN TELEGRAM
☔ ECON: Explicit Clothed #Avatars ☔
👉ECON: high-fidelity 3D humans even in loose clothes and challenging poses
😎Review https://bit.ly/3W21Wsu
😎Paper arxiv.org/pdf/2212.07422.pdf
😎Project https://xiuyuliang.cn/econ/
😎Code https://github.com/YuliangXiu/ECON
👉ECON: high-fidelity 3D humans even in loose clothes and challenging poses
😎Review https://bit.ly/3W21Wsu
😎Paper arxiv.org/pdf/2212.07422.pdf
😎Project https://xiuyuliang.cn/econ/
😎Code https://github.com/YuliangXiu/ECON
⚡1👍1🤯1
This media is not supported in your browser
VIEW IN TELEGRAM
🟥 3DHumanGAN: 3D Humans 🟥
👉 The first ever 3D-aware GAN for full-body humans is out!
😎Review https://bit.ly/3V07QJE
😎Paper arxiv.org/pdf/2212.07378.pdf
😎Code 3dhumangan.github.io/
😎Project github.com/3dhumangan/3DHumanGAN
👉 The first ever 3D-aware GAN for full-body humans is out!
😎Review https://bit.ly/3V07QJE
😎Paper arxiv.org/pdf/2212.07378.pdf
😎Code 3dhumangan.github.io/
😎Project github.com/3dhumangan/3DHumanGAN
🔥4🤯2🤩1
This media is not supported in your browser
VIEW IN TELEGRAM
🔍 DifFace: Super-Face Restoration 🔍
👉The new SOTA face restoration in severe-degradation photos
😎Review https://bit.ly/3YqCsXr
😎Paper arxiv.org/pdf/2212.06512.pdf
😎Code github.com/zsyOAOA/DifFace
👉The new SOTA face restoration in severe-degradation photos
😎Review https://bit.ly/3YqCsXr
😎Paper arxiv.org/pdf/2212.06512.pdf
😎Code github.com/zsyOAOA/DifFace
🤯9❤7👍5🤩1
Media is too big
VIEW IN TELEGRAM
🔥DRAMA of the week: ARTIST vs.#AI ART🔥
👉Generative AI is changing forever (again) how we create images, video and music. Progress brings conflict.
Let's talk: https://bit.ly/3BHOUIN
👉Generative AI is changing forever (again) how we create images, video and music. Progress brings conflict.
Let's talk: https://bit.ly/3BHOUIN
🤣6🥰1
This media is not supported in your browser
VIEW IN TELEGRAM
🖼️ PV3D: Generative Portrait Video 🖼️
👉 PV3D: first generative #AI for multi-view consistent portrait videos
😎Review https://bit.ly/3W5l5dn
😎Project showlab.github.io/pv3d/
😎Paper arxiv.org/pdf/2212.06384.pdf
👉 PV3D: first generative #AI for multi-view consistent portrait videos
😎Review https://bit.ly/3W5l5dn
😎Project showlab.github.io/pv3d/
😎Paper arxiv.org/pdf/2212.06384.pdf
👍4💩2🤯1
AI with Papers - Artificial Intelligence & Deep Learning
⚛️SOTA ALERT! Particles Tracking ⚛️ 👉The new SOTA in video particles tracking. "Old school" taste, with neural flavor 🧡 😎Review https://bit.ly/3CaU5Ai 😎Project particle-video-revisited.github.io/ 😎Paper arxiv.org/pdf/2204.04153.pdf 😎Code github.com/aharley/pips
This media is not supported in your browser
VIEW IN TELEGRAM
🔥 MODEL (and SOTA) UPDATE 🔥
👉 New PIPs checkpoint: 4x larger batch size and better performance than the "old" #ECCV2022 paper
👆 In the gif: tracking >5000 points on a camel (1.5s on #Nvidia RTX 3090)
👉 New PIPs checkpoint: 4x larger batch size and better performance than the "old" #ECCV2022 paper
👆 In the gif: tracking >5000 points on a camel (1.5s on #Nvidia RTX 3090)
👍5🔥3🤯3👏2
This media is not supported in your browser
VIEW IN TELEGRAM
🏜Insane Neural Asset by #META 🏜
👉DiffRF: novel 3D radiance field synthesis based on denoising diffusion
😎Review https://bit.ly/3V5Daqo
😎Project sirwyver.github.io/DiffRF/
😎Paper arxiv.org/pdf/2212.01206.pdf
👉DiffRF: novel 3D radiance field synthesis based on denoising diffusion
😎Review https://bit.ly/3V5Daqo
😎Project sirwyver.github.io/DiffRF/
😎Paper arxiv.org/pdf/2212.01206.pdf
😍7🤯4⚡1❤1
This media is not supported in your browser
VIEW IN TELEGRAM
🎸 RIFFUSION: #AI that sounds! 🎸
👉RIFFUSION: real-time music generation via spectrograms created with #stablediffusion
😎Review https://bit.ly/3GcOtcd
😎Project www.riffusion.com/about
😎App https://www.riffusion.com/
😎Code github.com/riffusion/riffusion-inference
😎Model huggingface.co/riffusion/riffusion-model-v1
👉RIFFUSION: real-time music generation via spectrograms created with #stablediffusion
😎Review https://bit.ly/3GcOtcd
😎Project www.riffusion.com/about
😎App https://www.riffusion.com/
😎Code github.com/riffusion/riffusion-inference
😎Model huggingface.co/riffusion/riffusion-model-v1
🤯7❤2🤩2⚡1👍1
This media is not supported in your browser
VIEW IN TELEGRAM
🪴 Rodin: 3D Avatars Using Diffusion 🪴
👉#Microsoft unveils a novel #3D diffusion for digital avatars as NeRF
😎Review https://bit.ly/3jcxeOX
😎Project 3d-avatar-diffusion.microsoft.com
😎Paper arxiv.org/pdf/2212.06135.pdf
👉#Microsoft unveils a novel #3D diffusion for digital avatars as NeRF
😎Review https://bit.ly/3jcxeOX
😎Project 3d-avatar-diffusion.microsoft.com
😎Paper arxiv.org/pdf/2212.06135.pdf
❤9🤯4👏2😱1
This media is not supported in your browser
VIEW IN TELEGRAM
🥻 Neural Cloth Simulation 🥻
👉The most advanced #AI for unsupervised garment animation
😎Review https://bit.ly/3WadOZR
😎Project
hbertiche.github.io/NeuralClothSim/
😎Paper
dl.acm.org/doi/pdf/10.1145/3550454.3555491
😎Code
https://github.com/hbertiche/NeuralClothSim
👉The most advanced #AI for unsupervised garment animation
😎Review https://bit.ly/3WadOZR
😎Project
hbertiche.github.io/NeuralClothSim/
😎Paper
dl.acm.org/doi/pdf/10.1145/3550454.3555491
😎Code
https://github.com/hbertiche/NeuralClothSim
🤯9👍4❤2
This media is not supported in your browser
VIEW IN TELEGRAM
🔥 #AIwithPapers: we are ~5,5k 🔥
👉 I see you: everyone hot for #CHATGPT. But Computer Vision still loves you. We miss you all, don't break up with us 🧡
😈 Forward this post!
😈 Let's talk -> https://bit.ly/3v389IT
😈 Invite -> https://t.iss.one/AI_DeepLearning
👉 I see you: everyone hot for #CHATGPT. But Computer Vision still loves you. We miss you all, don't break up with us 🧡
😈 Forward this post!
😈 Let's talk -> https://bit.ly/3v389IT
😈 Invite -> https://t.iss.one/AI_DeepLearning
🤣16❤8👍5🔥1👏1
This media is not supported in your browser
VIEW IN TELEGRAM
🤯 Point·E: the "DALL·E" of 3D pts cloud 🤯
👉OpenAI opens Point·E: the "evolution" of DALL·E in the #3D point cloud domain
😎Review https://bit.ly/3I87PR9
😎Code github.com/openai/point-e
😎Paper arxiv.org/pdf/2212.08751.pdf
👉OpenAI opens Point·E: the "evolution" of DALL·E in the #3D point cloud domain
😎Review https://bit.ly/3I87PR9
😎Code github.com/openai/point-e
😎Paper arxiv.org/pdf/2212.08751.pdf
🤯10❤2🍾2⚡1🔥1🤩1😍1
This media is not supported in your browser
VIEW IN TELEGRAM
🥑InstantAvatar: Avatar in 1 min.🥑
👉Avatars from monocular video in ONE minute (130x faster than SOTA)
😎Review https://bit.ly/3PNw1tJ
😎Paper arxiv.org/pdf/2212.10550.pdf
😎Project tijiang13.github.io/InstantAvatar
👉Avatars from monocular video in ONE minute (130x faster than SOTA)
😎Review https://bit.ly/3PNw1tJ
😎Paper arxiv.org/pdf/2212.10550.pdf
😎Project tijiang13.github.io/InstantAvatar
🤯4❤3⚡1👍1
This media is not supported in your browser
VIEW IN TELEGRAM
🐬 DeepLSD: Neural Lines Detector 🐬
👉 DeepLSD: novel neural line detector in the wild. Paper, Code, and Models available
😎Review https://bit.ly/3WqONK2
😎Paper arxiv.org/pdf/2212.07766.pdf
😎Code github.com/cvg/deeplsd
👉 DeepLSD: novel neural line detector in the wild. Paper, Code, and Models available
😎Review https://bit.ly/3WqONK2
😎Paper arxiv.org/pdf/2212.07766.pdf
😎Code github.com/cvg/deeplsd
🤯6🔥4🍾2⚡1👍1