🦚🦚#Nvidia open-sourcing EditGAN, first GAN-driven visual editor for high-precision semantic editing🦚🦚

👉GANs have recently found applications in image… | 13 comments on LinkedIn

🔞🦶This foot does not exist: GAN-based erotic service🦶🔞

👉GANs have recently found applications in dataset generation, image editing and many more.... 13 comments on LinkedIn

⚕️💊Impressive work by AstraZeneca on polypharmacy side-effect & combination synergy via #AI models💊⚕️

👉A unified theoretical view of relational machine...

🏀🥎DynaBOA: a novel #AI able to adapt the human mesh in "extreme" #AR, #VR, and sport contests 🥎🏀

👉Human mesh reconstruction shows remarkable real-world... 15 comments on LinkedIn

💹📊#Nvidia open-sourced TSPP: a "Time-Series Prediction Platform" for #PyTorch💹📊

Time-series prediction is a common problem in multiple domains for...

🐼🐸#kalidokit: an open-source "avatar-izer" for #Mediapipe / Tensorflow.js models🐸🐼

👉Kalidokit takes predicted #3D landmarks and calculates simple...

😈😈 The official #Pytorch implementation of PIXIE is out 😈😈

👉Expressive body with detailed face shape and hand articulation from a single image. ...

👋🙌#Google #AI just open-sourced a novel 2D/3D multi-hand tracking system for interactive apps 👋🙌

👉A new version of the hand pose detection, with ... 23 comments on LinkedIn

🤩🤩 Insanely detailed taxonomy of 𝗩𝗶𝘀𝘂𝗮𝗹 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀 🤩🤩

👉Transformer, an attention-based encoder-decoder architecture, has revolutionized...

🥬🥬#Nvidia unveils a novel framework to exploit simulation in #selfdrivingcars scenarios🥬🥬

👉In autonomous driving scenarios, the domain gap between...

👲🤡 BlendGAN: 𝗶𝗻𝗳𝗶𝗻𝗶𝘁𝗲 stylized faces with a single neural model 🤡👲

👉GANs have made a dramatic leap in HQ image synthesis. The layer-swapping...

🐍🐍Berkeley unveils HMAR, new SOTA in #3D multi-people tracking🐍🐍

👉Humans are three-dimensional beings, who live and move in a three-dimensional space...

🤖🤖#AI-driven holograms to reduce speckle in #AR / #VR applications 🤖🤖

👉While research on holographic displays has recently made impressive progress…

👲🤳 #Google to correct faces and lines distortion in video selfies👲🤳

👉Video selfies are often captured by wide-angle cameras to show human subjects...

🌅🌄#Nvidia unveils GauGAN2, live text-to-image #AI for landscapes generation 🌅🌄

👉GauGAN2, named after post-Impressionist painter Paul Gauguin, uses... 13 comments on LinkedIn

😚☺️Tencent #AI open-sourced HFGI: a GAN inversion framework to play with face details😚☺️

👉Image attribute editing is the task of modifying desired…

💎❌💎 THIS DIAMOND DOES NOT EXIST 💎❌💎

👉The artist makitrad trained a Stylegan3 #AI model to generate a crystal that does not exist. Want to buy the NFT? 👇…

🦙🦙#Samsung open-sourced LaMa, an #AI to erase objects from images🦙🦙

👉Image inpainting requires both to understand large-scale structure and to perform... 21 comments on LinkedIn

🛢️🪵#Google is open-sourcing SAVi, novel approach to extend the Slot Attention mechanism to videos🛢️🪵

👉Object-centric representations are a promising...

🚀🚀#Microsoft open-sourced NÜWA, unified framework for neural visual world creation (better than DALL·E)🚀🚀

👉Unified multimodal pretrained model to… | 12 comments on LinkedIn

🪐🌴IceVision is the first agnostic Computer Vision framework with hundreds of pre-trained models🪐🌴

👉A curated collection with hundreds of HQ pre-trained...