🪛PACE: new SOTA Motion🪛

👉#Nvidia unveils the novel SOTA to estimate the human motion in a global scene from moving cams. Stunning results.

😎Review https://t.ly/20you
😎Project https://nvlabs.github.io/PACE
😎Paper https://arxiv.org/pdf/2310.13768.pdf

🥤NanoSAM: SAM on low-cost boards🥤

👉NanoSAM is a Segment Anything variant capable of running in real-time on #NVIDIA Jetson Orin with TensorRT

😎Review https://t.ly/UErq_
😎Tutorial https://github.com/NVIDIA-AI-IOT/nanosam

🛋️ 3DiffTection: new SOTA 3D detection 🛋️

👉#Nvidia unveils 3DiffTection, the new SOTA for 3D object detection from single images. A powerful 3D detector powered by diffusion model

😎Review https://t.ly/PciXY
😎Paper https://arxiv.org/pdf/2311.04391.pdf
😎Code https://github.com/nv-tlabs/3DiffTection
😎Project research.nvidia.com/labs/toronto-ai/3difftection

🌦️ 100+ GPU weather training 🌦️

👉#NVIDIA just released Makani: massively parallel training of weather and climate prediction models on 100+ GPUs and to enable the development of the next generation of weather and climate models.

👉 Review https://t.ly/jageY
👉 Code https://lnkd.in/d4NFZ5xi

🔥 #6D Foundation Pose 🔥

👉#Nvidia unveils FoundationPose, a novel (and unified) foundation model for 6D object pose estimation and tracking.

👉Review https://t.ly/HGd4h
👉Project https://lnkd.in/dPcnBKWm
👉Paper https://lnkd.in/dixn_iHZ
👉Code coming 🩷

🦩 WildRGB-D: Objects in the Wild 🦩

👉#NVIDIA unveils a novel RGB-D object dataset captured in the wild: ~8500 recorded objects, ~20,000 RGBD videos, 46 categories with corresponding masks and 3D point clouds.

👉Review https://t.ly/WCqVz
👉Data github.com/wildrgbd/wildrgbd
👉Paper arxiv.org/pdf/2401.12592.pdf
👉Project wildrgbd.github.io/

🌆 Up to 69x Faster SAM 🌆

👉EfficientViT-SAM is a new family of accelerated Segment Anything Models. The same old SAM’s lightweight prompt encoder and mask decoder, while replacing the heavy image encoder with EfficientViT. Up to 69x faster, source code released. Authors: Tsinghua, MIT & #Nvidia

👉Review https://t.ly/zGiE9
👉Paper arxiv.org/pdf/2402.05008.pdf
👉Code github.com/mit-han-lab/efficientvit

🔌 BodyMAP: human body & pressure 🔌

👉#Nvidia (+CMU) unveils BodyMAP, the new SOTA in predicting body mesh (3D pose & shape) and 3D applied pressure on the human body. Source Code released, Dataset coming 💙

👉Review https://t.ly/8926S
👉Project bodymap3d.github.io/
👉Paper https://lnkd.in/gCxH4ev3
👉Code https://lnkd.in/gaifdy3q

📈Gradient Boosting Reinforcement Learning📈

👉#Nvidia unveils GBRL, a framework that extends the advantages of Gradient Boosting Trees to the RL domain. GBRL adapts the power of Gradient Boosting Trees to the unique challenges of RL environments, including non-stationarity and absence of predefined targets. Code released💙

👉Review https://t.ly/zv9pl
👉Paper https://arxiv.org/pdf/2407.08250
👉Code https://github.com/NVlabs/gbrl

🛳️ EVER Ellipsoid Rendering 🛳️

👉UCSD & Google present EVER, a novel method for real-time differentiable emission-only volume rendering. Unlike 3DGS it does not suffer from popping artifacts and view dependent density, achieving ∼30 FPS at 720p on #NVIDIA RTX4090.

👉Review https://t.ly/zAfGU
👉Paper arxiv.org/pdf/2410.01804
👉Project half-potato.gitlab.io/posts/ever/