Saurabh Saxena

@srbhsxn

Researcher at Google Deepmind

San Francisco, CA

saurabhsaxena.org

Joined September 2013

384 Following

1,200 Followers

Replies Reposts Media

Saurabh Saxena
@srbhsxn
Oct 23
I am seeking a highly motivated Student Researcher @GoogleDeepMind to work with my team on topics at the frontier of visual understanding and generative modeling! 🚀 If interested, please apply at forms.gle/ud2nhuFVvySgan…
5
Saurabh Saxena
@srbhsxn
Sep 8
Heading to #eccv2026 to present this work! I am looking for student researchers who are interested in long range world modelling and spatial understanding in VLMs. If you are attending ECCV and are interested in these topics, please reach out, I'd love to chat!
Ziyi Wu
@Dazitu_616
Jan 28
📢Introducing 360Anything, our method for lifting any perspective image or video to gravity-aligned 360° panoramas without using any camera or 3D information. This enables consistent novel view synthesis and 3D scene reconstruction. Project page: 360anything.github.io 🧵
1
Saurabh Saxena
@srbhsxn
Aug 27
Excited to finally release our benchmark from #CVPR2026 The core idea is simple: The wide FoV of 360° allows robust camera tracking so we can extract challenging perspective crops from 360° videos and leverage the cameras estimated from 360° as reliable groundtruth. Link in🧵👇
Sara Sabour
@sabour_sara
Aug 27
🚀 We are excited to release the dataset, code, and expanded paper for ORBIT++: Benchmarking SfM in the Wild with 360° Video! Following our initial publication at CVPR, we’re releasing the full benchmark and codebase: 🌐 Project: orbit-sfm.github.io 📄 arXiv:
Saurabh Saxena
@srbhsxn
Jan 28
High-fidelity 360s are crucial for generating 3D environments. This work, led by @Dazitu_616, "solves" 360° generation with a simple, scalable architecture, achieving remarkable 3D consistency. Check out the thread and website for an interactive viewer.
Ziyi Wu
@Dazitu_616
Jan 28
📢Introducing 360Anything, our method for lifting any perspective image or video to gravity-aligned 360° panoramas without using any camera or 3D information. This enables consistent novel view synthesis and 3D scene reconstruction. Project page: 360anything.github.io 🧵
1
Saurabh Saxena
@srbhsxn
Dec 12, 2025
Our team at Google DeepMind in Toronto is hiring student researchers for 2026 to work on cutting-edge vision research, focusing on both generative models and scene understanding. Come work with us! Apply at: forms.gle/qTEbEfwwQnModV…
5