👩‍🚀 HD Avatar via Text & Pose 👩‍🚀

👉 Generating expressive #3D avatars from nothing but text descriptions & pose guidance

😎Review https://t.ly/wrSMH
😎Paper arxiv.org/pdf/2308.03610.pdf
😎Project avatarverse3d.github.io

🐘 Controllable Synthetic Data (extending Image-Net) 🐘

👉#META's PUG, a new generation of interactive environments for representation learning. Extending Image-Net!

😎Review https://t.ly/nCYs0
😎Paper arxiv.org/pdf/2308.03977.pdf
😎Project pug.metademolab.com
😎Code github.com/facebookresearch/PUG

🔥The code is out!🔥

😎 Code https://github.com/NVlabs/neuralangelo

🌈 Tracking by Persistent Dynamic View Synthesis 🌈

👉Novel simultaneous addressing of dynamic scene novel-view synthesis + 6-DOF tracking of all dense scene elements

😎Review https://t.ly/Bc535
😎Paper arxiv.org/pdf/2308.09713.pdf
😎Project dynamic3dgaussians.github.io
😎Code github.com/JonathonLuiten/Dynamic3DGaussians

🛒 Digital Twins for AutoRetail Checkout 🛒

👉From #Nvidia a novel approach for using 3D assets for training 2D detection and tracking model in AutoRetail Checkout

😎Review https://t.ly/Ea7kt
😎Paper arxiv.org/pdf/2308.09708.pdf
😎Code github.com/yorkeyao/Automated-Retail-Checkout

🥎SportsMOT + MixSort = Sport MOT🥎

👉Nanjing just released a MOT dataset for sports scenes + the SOTA code/model for tracking (MixSort)

😎Review https://t.ly/NHUxL
😎Paper arxiv.org/pdf/2304.05170.pdf
😎Code github.com/MCG-NJU/MixSort
😎Project deeperaction.github.io/datasets/sportsmot.html

⚡️Feature Matching at Light Speed⚡️

👉LightGlue is a lightweight feature matcher with high accuracy and blazing fast inference

😎Review https://t.ly/jkecX
😎Paper arxiv.org/pdf/2306.13643.pdf
😎Code github.com/cvg/LightGlue

🕹️ CoDeF: Video Content Deformation Fields 🕹️

👉CoDeF is a new type of video representation for video-editing tasks

😎Review https://t.ly/PIVl-
😎Paper arxiv.org/pdf/2308.07926.pdf
😎Project https://qiuyu96.github.io/CoDeF
😎Code https://github.com/qiuyu96/CoDeF

Hello everybody,
a lot of you asked me to open the comments to better enjoy the posts. I want to follow your suggestion, hope you will enjoy this new mood!

🔥 NO SPAM
🔥 NO COMMERCIAL
🔥 NO UNRESPECTFUL MESSAGEs

🧡JUST AI & SCIENCE

⚠️ BAN AT THE FIRST VIOLATION ⚠️

🦠 Instance-Level Semantics of Cells 🦠

👉TYC: novel dataset for understanding instance-level semantics & motions of cells in microstructures

😎Review https://t.ly/y-4VZ
😎Paper arxiv.org/pdf/2308.12116.pdf
😎Project christophreich1996.github.io/tyc_dataset/
😎Code github.com/ChristophReich1996/TYC-Dataset
😎Data tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/3930

🌵POCO: 3D HPS + Confidence🌵

👉 Novel framework for HPS: #3D human body + confidence in a single feed-forward pass

😎Review https://t.ly/cDePe
😎Paper arxiv.org/pdf/2308.12965.pdf
😎Project https://poco.is.tue.mpg.de

🌆 NeO360: NeRF for Sparse Outdoor 🌆

👉#Toyota (+GIT) unveils NeO360: 360◦ outdoor scenes from a single or a few posed RGB images

😎Review https://t.ly/JDJZg
😎Paper arxiv.org/pdf/2308.12967.pdf
😎Project zubair-irshad.github.io/projects/neo360.html

🥕 Scenimefy: I-2-I for anime 🥕

👉S-Lab unveils a novel semi-supervised I-2-I translation framework + HD dataset for anime

😎Review https://t.ly/IsdEG
😎Paper arxiv.org/pdf/2308.12968.pdf
😎Code https://github.com/Yuxinn-J/Scenimefy
😎Project https://yuxinn-j.github.io/projects/Scenimefy.html

🐨 Watch Your Steps: Editing by Text 🐨

👉The novel SOTA in image & scene (text) editing via denoising diffusion models

😎Review https://t.ly/fv9wn
😎Paper arxiv.org/pdf/2308.08947.pdf
😎Project ashmrz.github.io/WatchYourSteps

💡 Relighting NeRF 💡

👉Neural implicit radiance representation for free viewpoint relighting of an object lit by a moving point light

😎Review https://t.ly/J-3_L
😎Project nrhints.github.io
😎Code github.com/iamNCJ/NRHints
😎Paper nrhints.github.io/pdfs/nrhints-sig23.pdf

🪶 ReST: Multi-Camera MOT 🪶

👉Novel reconfigurable two-steps graph model for multi-camera multi object video tracking (MC-MOT)

😎Review https://t.ly/3C5tb
😎Paper arxiv.org/pdf/2308.13229.pdf
😎Code github.com/chengche6230/ReST

🌲MagicEdit: Magic Video Edit🌲

👉MagicEdit: explicit disentangling content, structure & motion for Hi-Fi and temporally coherent video editing

😎Report https://t.ly/tREX4
😎Paper arxiv.org/pdf/2308.14749.pdf
😎Project magic-edit.github.io
😎Code github.com/magic-research/magic-edit

✂️ VideoCutLER: Simple UVIS ✂️

👉VideoCutLER is a simple unsupervised video instance segmentation (UVIS) method without relying on optical flows

😎Review https://t.ly/PBBjG
😎Paper arxiv.org/pdf/2308.14710.pdf
😎Project people.eecs.berkeley.edu/~xdwang/projects/CutLER
😎Code github.com/facebookresearch/CutLER/tree/main/videocutler

🐦 3D Pigeons Pose & Tracking 🐦

👉 3D-MuPPET: estimate and track 3D poses of pigeons with multiple-views

😎Review https://t.ly/jfAJJ
😎Paper arxiv.org/pdf/2308.15316.pdf
😎Code github.com/alexhang212/3D-MuPPET/