👋Forecasting interactions via attention👋

👉Predicting the hand motion trajectory and the future contact points on the next active object

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Object-Centric Transformer (OCT)
✅Self-attention Transformer mechanism
✅Framework to handle uncertainty
✅SOTA on Epic-Kitchens and EGTEA

More: https://bit.ly/3v3PpbI

🍇SmeLU: Smooth Activation Function🍇

👉Google unveils a new smooth activation function: easy to implement, cheap & less error-prone

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Smooth to mitigate irreproducibility
✅Cheap function, better than GELU/Swish
✅0-1 slope through quadratic middle region
✅SmeLU as convolution of ReLU with box
✅Best reproducibility-accuracy tradeoff

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

📍Hyper-Dense Landmarks at 150FPS📍

👉#Microsoft unveils the SOTA in dense landmarking + #3D reconstruction. MAGIC.

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Accurate 10× as many landmarks as usual
✅Synthetic data, perfect annotations
✅NO appearance, light, diff-rendering
✅#3D @150+FPS with a single CPU thread
✅SOTA in monocular 3D reconstruction

More: https://bit.ly/37pQS40

☀️SunStage: Selfie with the Sun☀️

👉Accurate/tailored reconstruction of facial geometry/reflectance

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Novel personalized scanning
✅Disentanglement of scene params
✅Geometry, materials, lighting, poses
✅Photorealistic with a single selfie video

More: https://bit.ly/36W1Oqx

📫 Generative Neural Avatars 📫

👉3D shapes of people in a variety of garments with corresponding skinning weight

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅ETH + Uni-Tübingen + Max Planck
✅Animatable #3D human in garment
✅Directly from raw posed 3D scans
✅NO canonical, registration, manual w.
✅Geometric detail in clothing deformation


More: https://bit.ly/3M7mCdB

🗨️Conversational program synthesis🗨️

👉Conversational synthesis to translate English into executable code

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Conversational program synthesis
✅New multi-turn progr.benchmark
✅Open Custom library: JAXFORMER
✅Source code under BSD-3 license

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

🧯Long Video Diffusion Models🧯

👉#Google unveils a novel diffusion model for video generation

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Straightforward extension of 2D UNet
✅Longer by new conditional generation
✅SOTA in unconditional generation

More: https://bit.ly/35Y2rzg

🚙 AutoRF: #3D objects in-the-wild 🚙

👉From #Meta: #3D object from just a single, in-the wild, image

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Novel view synthesis from in-the-wild
✅Normalized, object-centric representation
✅Disentangling shape, appearance & pose
✅Exploiting BBS & panoptic segmentation
✅Shape/appearance properties for objects


More: https://bit.ly/3O4ONeQ

🌠GAN-based Darkest Dataset🌠

👉Berkeley + #Intel announce first photorealistic dataset under starlight (no moon, <0.001 lx)

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅"Darkest" dataset ever seen
✅Moonless, no external illumination
✅GAN-tuned physics-based model
✅Clips with dancing, volleyball, flags...

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

🤖Populating with digital humans🤖

👉ETHZ unveils GAMMA to populate the #3D scene with digital humans

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅GenerAtive Motion primitive MArkers
✅Realistic, controllable, infinite motions
✅Tree-based search to preserve quality
✅SOTA in realistic/controllable motion

More: https://bit.ly/3OgY4AG

🔥#AIwithPapers: we are ~2,000!🔥

💙💛 Simply amazing. Thank you all 💙💛

😈 Invite your friends -> https://t.me/AI_DeepLearning

😼GARF: Gaussian Activated NeRF😼

👉GARF: Gaussian Activated R.F. for Hi-Fi reconstruction/pose

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅NeRF from imperfect camera poses
✅NO hyper-parameter tuning/initialization
✅Theoretical insight on Gaussian activation
✅Unlocking NeRF for real-world application?

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

🎭Novel pre-training strategy for #AI🎭

👉EPFL unveils the Multi-modal Multi-task Masked Autoencoders (MultiMAE)

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Multimodal: additional modal. over RGB
✅Multi-task: multiple outputs over RGB
✅General: MultiMAE by pseudo-labeling
✅Classification, segmentation, depth
✅Code under NonCommercial 4.0 Int.

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

🧪 A new SOTA in Dataset Distillation 🧪

👉A new approach by Matching Training Trajectories is out!

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Distilling data "to match" bigger one
✅Distilled data to guide a network
✅Trajectories of experts from real data
✅SOTA + distilling higher-res visual data

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

🧤 Two-Hand tracking via GCN 🧤

👉The first-ever GCN for two interacting hands in single RGB image

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Reconstruction by GCN mesh regression
✅PIFA: pyramid attention for local occlusion
✅CHA: cross hand attention for interaction
✅SOTA + generalization in-the-wild scenario
✅Source code available under GNU 🤯

More: https://bit.ly/3KH5FWO

🕹️Video K-Net, SOTA in Segmentation🕹️

👉Simple, strong, and unified framework for fully end-to-end video panoptic segmentation

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Learnable kernels from K-Net
✅K-Net learns to segment & track
✅Appearance / cross-T kernel interaction
✅New SOTA without bells and whistles 🤷‍♂️

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

🐭DeepLabCut: tracking animals in the wild🐭

👉A toolbox for markerless pose estimation of animals performing various tasks

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Multi-animal pose estimation
✅Datasets for multi-animal pose
✅Key-points, limbs, animal identity
✅Optimal key-points without input

More: https://bit.ly/37L1mLE

🍡Neural Articulated Human Body🍡

👉Novel neural implicit representation for articulated body

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅COmpositional Articulated People
✅Large variety of shapes & poses
✅Novel encoder-decoder architecture

More: https://bit.ly/3xvn7dl

🦚 2K Resolution Generative #AI 🦚

👉Novel continuous-scale training with variable output resolutions

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Mixed-resolution data
✅Arbitrary scales during training
✅Generations beyond 1024×1024
✅Variant of FID metric for scales
✅Source code under MIT license

More: https://bit.ly/3uNfVY6