✌️Two Transformers with NO CONVOLUTION can make one strong GAN☝️

👉TransGAN, consists of a memory-friendly transformer-based generator that progressively…

💥#Nvidia TLT 3.0 is out with a lot of pre-trained models💥

👉Creating a model from scratch can be daunting and expensive. NVIDIA TLT abstracts away the AI/DL…

💥This #AI learns obstacles for neural motion plan💥

👉Motion planning and obstacle avoidance is a key challenge in robotics applications. While previous...

😲MediaPipe #AI from Google updated for fitness/yoga practitioners😲

👉MediaPipe Pose is a ML solution for high-fidelity body pose tracking, inferring...

😲This #AI deals with effects 1000x faster😲

👉NeX is a new approach to novel view synthesis based on enhancements of multiplane image (MPI) that can ...

🥰 Can't stop watching this StyleGAN2 trained on Welsh Corgi 🥰

🚀 Want to know more about #AI and our projects? Follow ARGO Vision or ping Alessandro...

😲This #AI retains the textural details of the style in a semantically meaningful manner😲

👉It's the first ever algorithm enabling instant real-time ...

💥This tech from Google better removes the aliasing in rendering up to 22x faster💥

👉mip-NeRF extends NeRF to represent the scene at a continuously-valued...

👨‍🏫Facebook AI introduces MAGRAD, a brand new optimizer for #deeplearning that exceeds the performance of Adam👨‍🏫

👉 The new optimizer, called MAGRAD... 24 comments on LinkedIn

🔥🧨 Microsoft releases an #AI made by Convolutions + Transformers 🔥🧨

👉The Convolutional Vision Transformer (CvT) improves Vision Transformer (ViT)...

⭐⭐This #AI uses *MIRRORS* to largely improve the 3D human pose reconstruction⭐⭐

👉 Compared to general scenarios of 3D pose estimation from a single view...

🌎🌍🌏 An end-to-end #AI framework able to de-render the world's revolutionary artefacts 🌎🌍🌏

👉 Recent works show exciting results in unsupervised ...

🏆🧢 Make VGG-style ConvNets Great Again 🧢🏆

👉 RepVGG is a super simple ConvNet architecture achieving >80% top-1 accuracy on ImageNet with a stack...

🤯 Removing tattoos with this #AI project 🤯

👉This project born after watching Justin Bieber's "Anyone" Music Video (🤣). He had his tattoo covered up with…

⚡Adapting a source GAN to a target domain using very few images⚡

👉Training generative models, such as GANs, on a target domain containing a few examples...

💃This #AI could be a game-changer in fashion e-commerce💃

👉SCALE models 3D clothed humans with hundreds of articulated surface elements, resulting in…

💊This #AI from Facebook AI predicts effective drug combinations for complex diseases faster 💊

👉 CPA is a deep generative framework to learn effects of…

🏃⚡PP-YOLOv2: the novel object detector faster than YOLOv5🏃⚡

👉A collection of existing refinements to improve the performance of previous PP-YOLO through... 49 comments on LinkedIn

🎁From Alibaba Group a high-quality efficient pretraining on ImageNet-21K available for everyone🎁

👉ImageNet-1K serves as the primary dataset for pretraining…

🚄From Facebook AI a novel method to create photorealistic human avatars for telepresence🚄

👉Photorealistic rendering is an important ability for telepresence...