🎉 [CVPR 2025] ZeroMSF Code Release!
3D scene flow from a single camera, with no fine-tuning on new domains? That’s the challenge we tackled in Zero-MSF (Zero-shot Monocular Scene Flow).
💡 Motivation
Scene flow captures both geometry and motion, but existing methods crumble when moving beyond their training set. We asked: Can we build a foundation-style model that generalizes—out of the box—to any scene?
🔬 Our Answer
• Large-scale synthetic pre-training (1M+ dynamic samples)
• A unified geometry-motion parameterization
• Zero-shot inference on real-world videos—no extra training, just run it!
🤝 Huge Thanks
To my brilliant collaborators AbhishekBadki, HangSu, @0razio and my amazing advisor @jtompkin for making this possible.
👉 Dive In: https://t.co/Ib27sUdHHo
🎉 Thrilled to introduce nvTorchCam, our new #PyTorch library designed to support the development of models using camera geometry like plane-sweep volumes (PSV) and related concepts like sphere-sweep volumes or epipolar attention, in a camera model-agnostic way! 🚀
🔗 Code: https://t.co/2z3xqJDDN9
(1/6)
We have research #internships roles at @NVIDIAAI!!
Reach out if you're in a PhD program, and are interested in anything 3D (e.g., monocular/multi-view depth estimation, SLAM, SfM, etc.), anything optical/scene flow, anything novel view synthesis.
Join us tomorrow (Sunday June 14th) for our #CVPR2020 tutorial on novel view synthesis.
We'll be streaming all of it live! https://t.co/4ij0d5tEuR
Stream start at 9:15am PDT
Info https://t.co/IlVfoULDxl