🪛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

🧂 SOTA RGB-D Video Salient Object 🧂

👉 DCTNet+ (model) and RDVS(dataset) for a new SOTA in Video Saliency Object Detection

😎Review https://t.ly/DapLV
😎Code github.com/kerenfu/RDVS
😎Paper arxiv.org/pdf/2310.15482.pdf

✌️ Relighted 3D Hands 🤞

👉#META unveils Re:InterHand: a large dataset of relighted 3D interacting hands

😎Review https://t.ly/I1dQk
😎Paper arxiv.org/pdf/2310.17768.pdf
😎Project mks0601.github.io/ReInterHand
😎Data github.com/mks0601/ReInterHand

🍄 Video Understanding with GPT-4V(ision) 🍄

👉 #Microsoft unveils MM-Vid, the most advanced video understanding framework (w/ #chatgpt4). Impressive results on long-form videos & intricate tasks such as audio description & multimodal high-level comprehension

😎Review https://t.ly/RISMm
😎Paper arxiv.org/pdf/2310.19773.pdf
😎Project https://multimodal-vid.github.io

👣 Foot via Synthetic Data 👣

👉 50,000 synthetic/photorealistic foot images + a novel SOTA library for foot

😎Review https://t.ly/TVanP
😎Paper https://arxiv.org/pdf/2310.18279.pdf
😎Project https://ollieboyne.github.io/FOUND
😎Code https://github.com/OllieBoyne/FOUND

🚛 OYSTER: unsupervised detection w/ LIDAR 🚛

👉Waabi unveils OYSTER: a novel unsupervised object detection from LiDAR point clouds.

😎Review https://t.ly/EMi58
😎Project https://waabi.ai/oyster/
😎Paper arxiv.org/pdf/2311.02007.pdf

🔥GPT-4 Pass the Turing Test?🔥

👉No. I mean...not yet. Read this Paper from UC San Diego👇

😎Review https://t.ly/o8HgM
😎Paper https://arxiv.org/pdf/2310.20216.pdf

🥻SF: Towards Virtual Cloth🥻

👉SEA AI Lab unveils a novel #AI to recovery the garment sewing patterns from daily photos for #AR / #VR worlds

😎Review https://t.ly/MwpAV
😎Project https://sewformer.github.io/
😎Paper https://arxiv.org/pdf/2311.04218.pdf
😎Code https://github.com/sail-sg/sewformer

🛋️ 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

🐪 30x Faster Neural Scenes 🐪

👉 NeuRas: realistic real-time novel-view synthesis of VERY large scenes (>10000 m2 ). 30× faster rendering than previous SOTA w/ comparable or better realism

😎Review https://t.ly/ELJSE
😎Paper https://arxiv.org/pdf/2311.05607.pdf
😎Project https://waabi.ai/NeuRas/

🔥 Hu.ma.ne #AI Pin is out! 🔥

👉Hu.ma.ne just launched #AI Pin: the new standalone AI-powered screenless device. Running on the GPT-4 LLMs, suitable for real-time translation. #AI-powered camera and laser projector

😎 More https://t.ly/IvoN7

🫀 Segmentation of Human 🫀

👉TotalSegmentator_v2: segmenting 104 anatomical structures (27 organs, 59 bones, 10 muscles, 8 vessels) in CT. Now suitable in 3D Slicer, open source platform for image visualization.

😎Review https://t.ly/yHMm1
😎Code https://lnkd.in/dvgrbsCE
😎Paper https://lnkd.in/dkwHuuzU

🪐 Spacecraft Pose Estimation 🪐

👉SnT (Luxembourg) unveils the most advanced event-based dataset for Spacecrafts: Unreal Engine + data from ICNS simulator + Real images + Real event data acquired in lab

😎Review https://t.ly/m8JPB
😎Paper https://lnkd.in/d_edvc3n
😎Project https://lnkd.in/dPp375aY

🔥Florence-2: unified Computer Vision🔥

👉#Microsoft announces Florence-2: novel foundation model with unified, prompt-based, representation for a large variety of #computervision & vision-language task. One backbone -> multiple tasks!

👉Review https://t.ly/pOins
👉Paper arxiv.org/pdf/2311.06242.pdf
👉Project www.microsoft.com/en-us/research/project/projectflorence/

💥🚗 CrashCar101: Generative Damaged Cars💥🚗

👉 CrashCar101: procedural generation pipeline that damages 3D car models to obtain synthetic damaged cars paired with pixel-accurate annotations

👉 Review https://t.ly/pITHm
👉 Paper https://lnkd.in/dzp6q3T5
👉 Project https://lnkd.in/daRXg73N

🐓 Emu: image edit / video gen. 🐓

👉#Meta the new SOTA in text-to-video generation and instruction-based image editing

👉 Review https://t.ly/PMTBc
👉 Paper (images): https://lnkd.in/eVadH-QS
👉 Project https://lnkd.in/eG8eWUJY
👉 Paper (video): https://lnkd.in/eVadH-QS
👉 Project https://lnkd.in/eu6Zu6gp

🌦️ 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

🍿 Segmenting anything in 3D 🍿

👉 OmniSeg3D: omniversal segmentation method aims for segmenting anything in 3D all at once.

👉Review https://t.ly/Q0jrK
👉Paper https://lnkd.in/d9qpxXY9
👉Project https://oceanying.github.io/OmniSeg3D
👉Code (soon)

🔳 SOTA Semantic Boundary 🔳

👉Mobile-Seed, a lightweight, dual-task framework tailored for simultaneous semantic segmentation and boundary detection.

👉Review https://t.ly/GsArZ
👉Project whu-usi3dv.github.io/Mobile-Seed/
👉Paper arxiv.org/pdf/2311.12651.pdf
👉Code github.com/WHU-USI3DV/Mobile-Seed