🟦🟨 StyleGAN on Internet pics 🟦🟨

👉StyleGAN on raw uncurated images collected from Internet

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Outliers & multi-modal
✅Self-distillation approach
✅Self-filtering of outliers
✅Perceptual clustering

More: https://bit.ly/33Z1d5H

🦜The new SOTA for Unsupervised 🦜

👉Self-supervised transformer to discover objects in images

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Visual tokens as nodes in graph
✅Edges as connectivity score
✅The second smallest eV = fg
✅Suitable for unsupervised saliency
✅Weakly supervised obj. detection
✅Code under MIT License


More: https://bit.ly/3sqbFg3

🥦 GAN-generated CryptoPunks 🥦

👉A simple (and funny) SN-GAN to generate cryptopunks

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Spectral normalization (2018)
✅Easy to incorporate into training
✅A project by Teddy Koker 🎩

More: https://bit.ly/35C1rQI

🤪SEER: self-AI from BILLIONS pic🤪

👉META + INRIA trained models on billions of random images without any pre-processing or assumptions

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Self-supervised on pics from web
✅Discovering properties in datasets
✅More fair, less biased & less harmful
✅Better OOD generalization
✅Source code available!

More: https://bit.ly/3vy69dd

🐲A novel AI-controllable synthesis🐲

👉Modeling local semantic parts separately and synthesizing images in a compositional way

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Structure & texture locally controlled
✅Disentanglement between areas
✅Fine-grained editing of images
✅Extendible via transfer learning
✅Just accepted to #CVPR2022

More: https://bit.ly/3IBgkBy

🥣 #AI-Generation with Dream Fields 🥣

👉Neural rendering with multi-modal image and text representations

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Aligned image & text models
✅3D from natural language
✅No additional data
✅D.F. neural-scene

More: https://bit.ly/3Mhwm5D

🟪 Mip-NeRF 360 for unbounded scenes 🟪

👉An extension of NeRF to overcome the challenges presented by unbounded scenes

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Realistic synthesized views
✅Intricate/unbounded scenes
✅Detailed depth maps
✅Mean-squared error -54%
✅No code provided 😥

More: https://bit.ly/36ZxsD4

🐓 PINA: personal Neural Avatar 🐓

👉A novel method to acquire neural avatars from RGB-D videos

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅A virtual copy of themselves
✅Realistic clothing deformations
✅Shape & non-rigid deformation
✅Avatars from RGB-D sequences
✅Creative Commons Zero v1.0

More: https://bit.ly/3HAtRIh

🐦 EfficientVIS: new SOTA for VIS 🐦

👉Simultaneous classification, segmentation, and tracking multiple object instances in videos

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Efficient and fully end-to-end
✅Iterative query-video interaction
✅First RoI-wise clip-level RT-VIS
✅Requires 15× fewer epochs

More: https://bit.ly/3KfqurN

🐠#AI-clips from single frame🐠

👉Moving objects in #3D while generating a video by a sequence of desired actions

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅A playable environments
✅A single starting image🤯
✅Controllable camera
✅Unsupervised learning

More: https://bit.ly/35VDrYO

🧊Kubric: AI dataset generator🧊

👉Open-source #Python framework for photo-realistic scenes: full control, rich annotations, TBs of fresh data 🤯

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Synthetic datasets with GT
✅From NeRF to optical flow
✅Full control over data
✅Ok privacy & licensing
✅Apache License 2.0

More: https://bit.ly/3hQCaFs

🪂µTransfer for enormous NNs 🪂

👉Microsoft unveils how to tune enormous neural networks

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅New HP tuning: µTransfer
✅Zero-shot transfer to full-model
✅Outperforming BERT-large
✅Outperforming 6.7B GPT-3
✅Code under MIT license

More: https://bit.ly/3qc37Ij

🐧Semantic via only text supervision🐧

👉GroupViT with a text encoder on a large-scale image-text dataset: semantic with any pixel-level annotations in training!

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Hierarc. Grouping Vision Transf.
✅Additional text encoder
✅NO pixel-level annotations
✅Semantic-seg task via zero-shot
✅Source code available soon

More:https://bit.ly/3hPGeWr

⌚4D-Net: Lidar + RGB synchronization⌚

👉Google unveils 4D-Net to combine 3D LiDAR and onboard RGB camera

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Point clouds/images in time
✅Fusing multiple modalities in 4D
✅Novel sampling for 3D P.C. in time
✅New SOTA for 3D detection

More: https://bit.ly/3hZCFwN

🐌 New SOTA in video synthesis! 🐌

👉Snap unveils a novel multimodal video generation framework via text/images

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Multimodal video generation
✅Bidirectional transformer
✅Video token with self-learn.
✅Text augmentation for robustness
✅Longer sequence synthesis

More: https://bit.ly/3hZLXsG

🎁 StyelNeRF source code is out 🎁

👉3D consistent photo-realistic image synthesis

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅NeRF + style generator
✅3D consistency for HD image
✅Novel regularization loss
✅Camera control on styles

More: https://bit.ly/3t5xC49

🦎CLD-based generative #AI by #Nvidia🦎

👉Nvidia unveils a novel critically-damped Langevin diffusion (CLD) for synthetic data

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅A novel diffusion process for SGMs
✅Novel score matching obj. for CLD
✅Hybrid denoising score matching
✅Efficient sampling from CLD model
✅Source code under a specific license

More: https://bit.ly/35MToBe

🛸UFO: segmentation @140+ FPS🛸

👉Unified Transformer Framework for Co-Segmentation, Co-Saliency & Salient Object Detection. All in one!

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Unified framework for co-segmentation
✅Co-segmentation, co-saliency, saliency
✅Block for long-range dependencies
✅Able to reach for 140 FPS in inference
✅The new SOTA on multiple datasets
✅Source code under MIT License

More: https://bit.ly/3KLd9b9

👗 Multi-GANs fashion 👗

👉Global GAN blended with other GANs for faces, shoes, etc.

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Multi-GAN framework
✅Several generators
✅Free of artifacts
✅Full-body generation
✅Humans, 1024x1024

More: https://bit.ly/37mfOte

🚧 FLAG: #3D Avatar Generation 🚧

👉A flow-based generative model of the 3D human body from sparse observations.

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅FLow-based Avatar Generative
✅Conditional distro of body pose
✅Exact pose likelihood process
✅Invertibility -> oracle latent code

More: https://bit.ly/3CQpk3p