🔥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

Sharing something exciting we've been working on as a Thanksgiving gift: Diffusion Self-Distillation (DSD), which redefines zero-shot customized image generation using FLUX. DSD is like DreamBooth, but zero-shot/training-free. It works across any input subject and desired

Monocular Dynamic Gaussian Splatting is Fast and Brittle but Smooth Motion Helps Yiqing Liang, Mikhail Okunev, Mikaela Angelina Uy, Runfeng Li, Leonidas Guibas, James Tompkin, Adam W. Harley tl;dr: benchmark for monocular dynamic GS arxiv.org/abs/2412.04457

📢 Our WACV #WACV2025 paper EgoPoints: Advancing Point Tracking for Egocentric Videos Now on ArXiv A benchmark (EgoPoints), semi-synthetic fine-tuning sequences (K-EPIC) and new evaluation metrics for re-ID of points arxiv.org/abs/2412.04592 ahmaddarkhalil.github.io/EgoPoints/ 🧵

Really excited to put together this #CVPR2025 workshop on "4D Vision: Modeling the Dynamic World" -- one of the most fascinating areas in computer vision today! We've invited incredible researchers who are leading fantastic work at various related fields. 4dvisionworkshop.github.io

Call for Papers: #CVPR2025 PixFoundation Workshop! Submissions are now open! Share your latest contributions and connect with the community! 🙌 📅 Deadline: March 4, 2025 sites.google.com/view/pixfounda…

Join us for the 4D Vision Workshop #CVPR2025 on June 11 starting at 9:20am! We'll have an incredible lineup of speakers discussing the frontier of 3D computer vision techniques for dynamic world modeling across spatial AI, robotics, astrophysics, and more. 4dvisionworkshop.github.io

Are Vision Foundation Models ready to tackle pixel-level tasks? 🖼️ Join us at the Pixel-level Vision Foundation Models (PixFoundation) Workshop at #CVPR2025! We’re excited to introduce an outstanding lineup of invited speakers. Meet them below 👇

We are excited for our CVPR 2025 PixFoundation workshop in #CVPR2025 2025. Note our workshop start is @ 8:30 am in room 101 E Music City Center. Our first two speakers: F. Güney is an assistant professor in Koc university, and Adam W. Harley is a research scientist in Meta.

Starting the day #CVPR2025 at the 4D Vision workshop with Adam W. Harley speaking about 4D structure, slowness and data driven needs.

Preprint of (not) today: Harley et al., "AllTracker: Efficient Dense Point Tracking at High Resolution" -- alltracker.github.io Efficient architecture to track all points/pixels in real-time. Matches multiple frames in real time at high resolution via RNN-based refinement.

Happy to report that AllTracker was accepted to #ICCV2025! The twists and turns and methodical experimentation here took at least 12 months in all. Super hard project, though in retrospect our solution is pretty simple. code: github.com/aharley/alltra… paper: arxiv.org/abs/2506.07310

Tricky sample for AllTracker. It has never seen water at training time, so I'm glad it knows to quickly discard the tracks there... The bird that travels right-to-left (behind the wings most of the time) could be handled better.

Yup! But I wouldn't say "single shot" -- AllTracker, inheriting from CoTracker and PIPs and RAFT, is an iterative approach. In practice, we iterate 4x to get the final answer (and this sums to 11 FPS at 576x1024).