🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images abs: arxiv.org/abs/2207.11148 project page: infinite-nature-zero.github.io

Check out our CVPR 2023 Award Candidate paper, DynIBaR! dynibar.github.io DynIBaR takes monocular videos of dynamic scenes and renders novel views in space and time. It addresses limitations of prior dynamic NeRF methods, rendering much higher quality views.

Doppelgangers: Learning to Disambiguate Images of Similar Structures paper page: huggingface.co/papers/2309.02… We consider the visual disambiguation task of determining whether a pair of visually similar images depict the same or distinct 3D surfaces (e.g., the same or opposite sides

.Qianqian Wang's 🎉Best Student Paper🎉 is being presented at #ICCV2023 tomorrow (Friday)! ▶️"Tracking Everything Everywhere All At Once"◀️ w/ Yen-Yu Chang, Ruojin Cai Zhengqi Li Bharath Hariharan Noah Snavely Friday Afternoon Oral & Poster! Come say hi! omnimotion.github.io

SpatialTracker Tracking Any 2D Pixels in 3D Space Recovering dense and long-range pixel motion in videos is a challenging problem. Part of the difficulty arises from the 3D-to-2D projection process, leading to occlusions and discontinuities in the 2D motion domain.

#CVPR If you are interested in how to extract the 3D trajectories from monocular video, do not miss our poster Tomorrow: Poster #84 (Arch 4A-E) SpatialTracker: Tracking Any 2D Pixels in 3D Space Web: henry123-boy.github.io/SpaTracker/ I and Qianqian Wang will be there, welcome to say hi!

Robot See, Robot Do allows you to teach a robot articulated manipulation with just your hands and a phone! RSRD imitates from 1) an object scan and 2) a human demonstration video, reconstructing 3D motion to plan a robot trajectory. robot-see-robot-do.github.io #CoRL2024 (Oral)

Introducing MegaSaM! 🎥 Accurate, fast, & robust structure + camera estimation from casual monocular videos of dynamic scenes! MegaSaM outputs camera parameters and consistent video depth, scaling to long videos with unconstrained camera paths and complex scene dynamics!

1/3 Today, an anecdote shared by an invited speaker at #NeurIPS2024 left many Chinese scholars, myself included, feeling uncomfortable. As a community, I believe we should take a moment to reflect on why such remarks in public discourse can be offensive and harmful.

We have released our code and model! github.com/CUT3R/CUT3R

Introducing St4RTrack!🖖 Simultaneous 4D Reconstruction and Tracking in the world coordinate feed-forwardly, just by changing the meaning of two pointmaps! st4rtrack.github.io

📢 Call for Papers: End-to-End 3D Learning @ ICCV 2025 Workshop Advance 3D Representation, Geometry & Generative AI for Robotics, Autonomous Driving, XR, and Science. 🌍 Domain-leading speakers 🏆 Best Paper Award 🗓 Submission Deadline: June 29 🔗 e2e3d.github.io

We're grateful to receive multiple sponsorships (to be announced soon)! 🏆 $1000 Best Paper Award 🏆 $1000 Best Demo Paper Award 🎁 Onsite gifts for attendees! Join us to shape the future of 3D learning in robotics, autonomous driving, the metaverse, and scientific imaging! 🔗

What would a World Model look like if we start from a real embodied agent acting in the real world? It has to have: 1) A real, physically grounded and complex action space—not just abstract control signals. 2) Diverse, real-life scenarios and activities. Or in short: It has to