🔥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

Good luck to my team and to thousands of vision researchers around the world. I am so grateful to have such a wonderful group, and to have such a rewarding job!

rendering CVX really looks interesting

MoSca-Version2: Dynamic Gaussian Fusion from Casual Videos via 4D Motion... youtu.be/7WrG5-xH1_k?si… via YouTube

Capture a scene with 2DGS that can be viewed from extremely close and far away viewpoints, without aliasing while maintaining detailed texture. Check our new work timsong412.github.io/HDGS-ProjPage/ lead by TimSong Heguang Lin and advised by me, Lingjie Liu and Kostas Daniilidis

I really like this work, which develops a neural network based on a well-known geometric insight. See you tmr in the afternoon!

Our new paper, "Spectral Image Tokenizer", is on arXiv! We train a tokenizer on DWT coefficients that enables autoregressive coarse-to-fine image generation, w/ applications to multiscale text-to-image, and text-guided editing. w/ Ameesh Makadia, Suhail Mohammed arxiv.org/abs/2412.09607

VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment Wenyan Cong, Kevin Wang, Jiahui, Colton Stearns, Yuanhao Cai, Dilin Wang, Rakesh Ranjan, Matt Feiszli, Leonidas Guibas, Zhangyang Wang, Weiyao Wang, @WayneINR arxiv.org/abs/2501.01949

ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking Tingyang Zhang, Chen Wang, Zhiyang (Frank) Dou, Qingzhe Gao, Jiahui, Baoquan Chen, Lingjie Liu tl;dr: probabilistic integration->optical flow predictions+long-term corres. arxiv.org/abs/2501.03220

📢 Calling all PhD students in Computer Graphics! The submission deadline for the #Eurographics2025 Doctoral Consortium is just one week away (Feb 13)! Don't miss this opportunity to present your research, receive expert feedback, and connect with fellow PhD students. 📝 Apply

Join us for the 2nd workshop on Equivariant Vision: From Theory to Practice #CVPR2025 on June 11, at Room 101C! Enjoy the exciting talks by Robin Walters Maani Ghaffari Taco Cohen Gabriele Cesa Prof. Tess Smidt Vincent Sitzmann Tommy Mitchel More details at: equivision.github.io

Claude will be a nice advisor, for those interested in neuromorphic, event l, and embodied ai this is a good opportunity at JHU

After studying 4D for the whole phd, finally we have the first 4D VISION workshop!! will be in 4D vision room for almost whole day tomorrow, come and join us!

The 4D vision workshop is so popular as the organizer I can’t even enter the main room there is a zoom room next to our main room! 🤣

We are presenting MoSca at Hall-D #70 #CVPR2025

tonight i became a doctor🤓

cool GRASPee