🗿DirectMHP: Multi-Head Pose Estimation🗿

👉Novel E2E multi-person head pose estimation (MPHPE) under full-range angles

😎Review https://bit.ly/3HJubXg
😎Paper arxiv.org/pdf/2302.01110.pdf
😎Code github.com/hnuzhy/DirectMHP

🧱 LEGO-Net: Objects in Rooms 🧱

👉Transformer-based iterative method for rearrangement of objects in messy rooms

😎Review https://bit.ly/3HR0fs6
😎Paper arxiv.org/pdf/2301.09629.pdf
😎Project ivl.cs.brown.edu/#/projects/lego-net

🎃 In-N-Out: 3D-aware OOD video editing 🎃

👉Novel 3D-aware video editing able to manipulate OOD objects (e.g. heavy makeup, accessories)

😎Review https://bit.ly/3jN0CMu
😎Paper arxiv.org/pdf/2302.04871.pdf
😎Project https://in-n-out-3d.github.io

🥸 MEGANE: Generative Morphable Eyeglass 🥸

👉#META unveils the most advanced #3D compositional morphable AI for eyeglasses (HD geometry/photometric interaction)

😎Review https://bit.ly/3jOWifu
😎Paper arxiv.org/pdf/2302.04868.pdf
😎Project junxuan-li.github.io/megane

💘 3D-aware Blending with NeRF 💘

👉Novel 3D-aware blending method via generative NeRFs

😎Review https://bit.ly/3lBEJA2
😎Paper arxiv.org/pdf/2302.06608.pdf
😎Project blandocs.github.io/blendnerf
😎Code github.com/naver-ai/BlendNeRF

🌅 Semantics-guided natural synthesis 🌅

👉Alibaba #AI unveils a novel semantics-guided synthesis of natural scenes

😎Review https://bit.ly/4115MVJ
😎Paper arxiv.org/pdf/2302.07224.pdf
😎Project zju3dv.github.io/paintingnature

🦞 SOTA ALERT: YOWOv2 is out! 🦞

👉 The 2nd-gen of YOWO, real-time detection of spatio-temporal actions

😎Review https://bit.ly/3IscY60
😎Paper arxiv.org/pdf/2302.06848v1.pdf
😎Code github.com/yjh0410/YOWOv2

📬 DIVOTrack: crossview MOT dataset 📬

👉 DIVOTrack + CrossMOT: the ultimate solution for MOT in realistic scenario

😎Review https://bit.ly/3YSFZgL
😎Paper arxiv.org/pdf/2302.07676.pdf
😎Code github.com/shengyuhao/DIVOTrack

🦩 One-Shot Face via LSs of StyleGAN2 🦩

👉 Novel video generation framework with edits, facial motions, deformations & identity

😎Review https://bit.ly/3xuChhF
😎Paper arxiv.org/pdf/2302.07848.pdf
😎Project trevineoorloff.github.io/FaceVideoReenactment_HybridLatents.io/

🌶️ 3D-aware conditional generative AI 🌶️

👉 Pix2Pix3D: 3D-aware conditional generative AI for controllable photorealistic synthesis

😎Review https://bit.ly/3I80MWS
😎Paper arxiv.org/pdf/2302.08509.pdf
😎Project www.cs.cmu.edu/~pix2pix3D
😎Code github.com/dunbar12138/pix2pix3D

🛡️ TPV: Tesla's O-Net competitor 🛡️

👉From Beijing an open-source approach for vision-centric autonomous driving #3D perception

😎Review https://bit.ly/3lNvVYc
😎Paper arxiv.org/pdf/2302.07817.pdf
😎Code github.com/wzzheng/TPVFormer

🏀 #NBA Mixed Reality is NUTS 🏀

👉The premiere of the streaming app of the #NBA is totally INSANE. A mix of #AI, CG and much more👇

🏀More: https://bit.ly/3IJ3uUp

🫳 Neural Relighting of Hands 🫴

👉#META unveil the first neural relighting for personalized hands in real-time under novel illumination

😎Review https://bit.ly/3SblmKC
😎Paper arxiv.org/pdf/2302.04866.pdf
😎Project sh8.io/#/relightable_hands

🪁 VoxFormer: 2D->#3D Voxel ViT🪁

👉#Nvidia VoxFormer: #3D volumetric semantics from 2D images

😎Review https://bit.ly/3Kw9Yab
😎Paper arxiv.org/pdf/2302.12251.pdf
😎Code github.com/NVlabs/VoxFormer

🪞DisCO: Selfie Correction with 3D-GAN🪞

👉Snap (et al.) unveils a GAN-based method for correcting distortions in close-up faces

😎Review https://bit.ly/3StGGuX
😎Paper arxiv.org/pdf/2302.12253.pdf
😎Project https://portrait-disco.github.io

⚽️ Vid2Avatar: 3D Avatar from Videos ⚽️

👉Vid2Avatar: detailed 3D avatar from monocular videos in the wild

😎Review https://bit.ly/3ISbceD
😎Paper arxiv.org/pdf/2302.11566.pdf
😎Project moygcc.github.io/vid2avatar
😎Code (soon) github.com/MoyGcc

🏉 SLAHMR: 4D People from Clip in-the-Wild 🏉

👉UC-Berkeley unveils SLAHMR: novel method to reconstruct global human trajectories from videos

😎Review https://bit.ly/3SzTIaj
😎Paper arxiv.org/pdf/2302.12827.pdf
😎Project vye16.github.io/slahmr/
😎Code github.com/vye16/slahmr

🐇 SplineCam: Neural Decision Boundary 🐇

👉#META -> SplineCam: a step towards neural visualization / interpretability

😎Review https://bit.ly/3mgoOaH
😎Paper arxiv.org/pdf/2302.12828.pdf
😎Project imtiazhumayun.github.io/splinecam
😎Code github.com/AhmedImtiazPrio/SplineCAM

👑 ControNet: Conditional Control of Diffusion 👑

👉Controlling Stable Diffusion via conditional inputs like edges, segmentation, keypoints, etc. Extra: a super-nice tutorial.

😎Review https://bit.ly/3YgjrWt
😎Paper arxiv.org/pdf/2302.05543.pdf
😎Code github.com/lllyasviel/ControlNet
😎Tutorial https://github.com/Mikubill/sd-webui-controlnet/discussions/204

🛸 TAU: video traffic analytics via UAVs 🛸

👉 Prince Sultan University unveils TAU: AI-integrated video analytics framework from UAVs' POV

😎Review https://bit.ly/3EQIh8F
😎Paper arxiv.org/pdf/2303.00337.pdf
😎Project github.com/bilel-bj/TAU

🩻 Independent Tokens for 3D Human 🩻

👉Tencent open-sourcing a novel method to estimate #3D human pose and shape from monocular videos

😎Review https://bit.ly/3Zz0uiH
😎Paper arxiv.org/pdf/2303.00298.pdf
😎Code github.com/yangsenius/INT_HMR_Model
😎Project yangsenius.github.io/INT_HMR_Model/index.html