🔥 Source Code of Box2mask is out! 🔥

👉BoxInstSeg is a toolbox for SOTA box-supervised instance segmentation

😎Review https://www.linkedin.com/posts/visionarynet_artificialintelligence-machinelearning-ml-activity-7018140723552108544-2yrq

😎Code github.com/LiWentomng/BoxInstSeg

🗣️ MemFace: Generative Talking Face 🗣️

👉#Microsoft (+SJTU) unveils MemFace: the new SOTA in talking faces generation

😎Review https://bit.ly/3k8TjhZ
😎Paper arxiv.org/pdf/2212.05005v2.pdf
😎Project memoryface.github.io/

🪛 AgileAvatar: HQ stylized 3D #Avatar 🪛

👉#ByteDance unveils a novel self-supervised framework for #3D avatars

😎Review https://bit.ly/3kaOAw6
😎Project ssangx.github.io/projects/agileavatar
😎Paper ssangx.github.io/pubs/2022-SIGGRAPHAsia-AgileAvatar.pdf

🔥 #Nvidia GC ViT Large -> updated! 🔥

👉The new SOTA (with large margin) across image classification, detection & semantic segmentation!

😎Review https://bit.ly/3W4ChyF
😎Code github.com/NVlabs/GCViT
😎Paper arxiv.org/pdf/2206.09959.pdf

🎛️ VecGAN: DETAILED Face Manipulation 🎛️

👉 VecGAN: SOTA I2I for facial editing with interpretable latent directions

😎Review https://bit.ly/3GGNUpZ
😎Project yusufdalva.github.io/vecgan/
😎Code github.com/yusufdalva/VecGAN
😎Paper arxiv.org/pdf/2207.03411.pdf

🧊 HOTCOLD: Thermal Adv-Fashion 🧊

👉A novel physical attack for IR cams via wearable temperature-sensitive patches

😎Review https://bit.ly/3k8mt0B
😎Paper arxiv.org/pdf/2212.05709.pdf
😎Code github.com/weihui1308/HOTCOLDBlock

👛 New Task in #AI: Domain Expansion 👛

👉#Adobe on augmenting the space a model can generate, without overriding its original behavior

😎Review https://bit.ly/3ZCtwPA
😎Paper arxiv.org/pdf/2301.05225.pdf
😎Project yotamnitzan.github.io/domain-expansion
😎Code github.com/adobe-research/domain-expansion

🍏 MMEditing: SOTA toolbox for #AI 🍏

👉An open-source image/video editing toolbox based on #PyTorch

😎Review https://bit.ly/3k4cmK8
😎Project github.com/open-mmlab/mmediting

📶 Dense Pose from WiFi 📶

👉AI able to map phase/amplitude of WiFi signals for human sensing application

😎Review https://bit.ly/3QDeFQC
😎Paper arxiv.org/pdf/2301.00250.pdf

🏵️ Instant-NeRF Artists Gallery 🏵️

👉A gallery of beautiful scenes powered by the #NVIDIA Instant-NeRF

😎Review https://bit.ly/3XxV9au
😎Gallery www.nvidia.com/en-us/research/ai-art-gallery/instant-nerf

🪷 Saliency Detection by/for Impaired 🪷

👉A novel dataset using images taken by visually impaired people. Suitable for (big object/text) saliency detectors

😎Paper arxiv.org/pdf/2301.05323.pdf
😎Data vizwiz.org/tasks-and-datasets/salient-object-detection
😎Code vizwiz.org/wp-content/uploads/2023/01/sod_mask_example.txt

🧪 YOLOv6 v3.0 is out! 🧪

👉Meituan open-sourced YOLOv6 v3.0: many novel enhancements on architecture & training scheme. New SOTA on COCO!

😎Review https://bit.ly/3wbj7wC
😎Paper arxiv.org/pdf/2301.05586.pdf
😎Code github.com/meituan/YOLOv6

🥫 Plug 'n' play self-checkout 🥫

👉#Google's new shelf-checking #AI: recognizing billions of products, even purchased/moved

😎Review https://bit.ly/3J58hQe
😎News https://cloud.google.com/blog/transform/nrf-2023-google-cloud-big-show-big-moment-hybrid-retail

🍊 GLIGEN: Grounded T2I Diffusion 🍊

👉New (insane🤯) SOTA in zero-shot layout-to-image generation. Demo available!

😎Review https://bit.ly/3J0rnHw
😎Paper arxiv.org/pdf/2301.07093.pdf
😎Code github.com/gligen/GLIGEN
😎Demo dev.hliu.cc/gligen_mirror2/
😎Project gligen.github.io/

🧤 Handy: Hands "Pipeline" by #Shopify 🧤

👉Shopify open-sourced Handy: hand gestures via #metaquest headsets -> into #Blender

😎Review https://bit.ly/3Wpkpi2
😎Project github.com/Shopify/handy
😎Demo diegomacario.github.io/Hands-In-The-Web/public/index.html

🍀 NeRF2NeRF: 3D registration on NeRFs 🍀

👉A novel 3D registration that operates directly on NeRFs

😎Review https://bit.ly/3ZRgz4a
😎Paper arxiv.org/pdf/2211.01600.pdf
😎Code github.com/nerf2nerf
😎Project https://nerf2nerf.github.io/
😎Dataset https://drive.google.com/drive/folders/1jNpwAv1T1ntjIHUMJ1wABePA2Z8_nRRQ

🎨 RecolorNeRF: #3D Color Editing 🎨

👉INSANE palette-based color editing of NeRF scenes

😎Review https://bit.ly/3GYjhfR
😎Paper arxiv.org/pdf/2301.07958.pdf
😎Project sites.google.com/view/recolornerf

🏞OmniObject3D: Realistic 3D Dataset 🏞

👉Large-vocabulary #3D dataset for realistic perception, reconstruction & generation

😎Review https://bit.ly/3HlXyjp
😎Paper arxiv.org/pdf/2301.07525.pdf
😎Project omniobject3d.github.io/

👑 OnePose++: One-Shot Pose 👑

👉Open-source (insane) keypoint-free pose pipeline for #AR

😎Review https://bit.ly/3kF0BdG
😎Paper arxiv.org/pdf/2301.07673.pdf
😎Project zju3dv.github.io/onepose_plus_plus
😎Code github.com/zju3dv/OnePose_Plus_Plus
😎Dataset zjueducn-my.sharepoint.com/personal/12121064_zju_edu_cn/_layouts/15/onedrive.aspx

🍄 BTS: Density Fields from Single View 🍄

👉Volumetric scene representation from a single image in challenging conditions

😎Review https://bit.ly/3wjHDvH
😎Paper arxiv.org/pdf/2301.07668.pdf
😎Project fwmb.github.io/bts/

⚡StyleGAN-T: unlocking Power of GANs⚡

👉#Nvidia unveils StyleGAN-T to regain competitiveness to GANs vs. Diffusive Models

😎Review https://bit.ly/3HtKxEA
😎Paper arxiv.org/pdf/2301.09515.pdf
😎Project sites.google.com/view/stylegan-t
😎Code github.com/autonomousvision/stylegan-t