QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videos Contributions: • We propose a Gaussian residual-based framework to model 3D dynamic scenes for online FVV without any structural constraints. This allows free learning of all 3D-GS

Excited to be WiML mentor tables, come join us!

👑 QUEEN captures high-quality free-viewpoint videos and reduces the model size to 0.7 MB / frame while training in under 5 sec and rendering at 350 FPS #NeurIPS2024 Sharath Girish Tianye Li amrita Abhinav Shrivastava David Luebke Shalini De Mello NVIDIA NVIDIA AI Univ. of Maryland

Sharath Girish amrita Abhinav Shrivastava David Luebke Shalini De Mello NVIDIA NVIDIA AI Univ. of Maryland amrita will present our poster on Friday 4:30-7:30pm. Please say hi 😀 neurips.cc/virtual/2024/p… #NeurIPS2024 🌐 website: research.nvidia.com/labs/amri/proj… 📄 paper: arxiv.org/abs/2412.04469

Sharath Girish amrita Abhinav Shrivastava David Luebke Shalini De Mello NVIDIA NVIDIA AI Univ. of Maryland Check out our poster! East Exhibit Hall A-C #1201 Fri 13 Dec 4:30 - 7:30 pm PST 👑 QUEEN simultaneously reconstructs the dynamic scene and compresses the model size to just 0.7 MB per frame while training in under 5 sec and rendering at 350 FPS. #NeurIPS2024 #NVIDIAResearch

Applications are open for WiGRAPH's 2025 Rising Stars program! Apply here: wigraph.org/programs/risin…

The 2nd workshop on Computer Vision for Videogames will be organized at CVPR 2025: this is a great venue for gaming-related research (think AI, genAI, graphics, RL, agents, HCI — with applications to videogames). There is still time to submit: sites.google.com/view/cv2-2025/ #CVPR2025

Our team is demonstrating immersive 3D video experiences at #GTC2025. Please come to the XR pavilion at the Tech Interactive. Website: research.nvidia.com/labs/amri/proj… #NVIDIA #VolumetricVideo #3DVideo #3DGS

📣 We have released the source code of 3DGRT and 3DGUT in a common 3DGRUT repo under the Apache license! Go try it out and play with our playground app!

Don't miss the "Volumetric Video in the Real World" tutorial at #CVPR2025 on 6/11 Hear from top academic & industry experts on innovations, opportunities and challenges in 4D reconstruction and generation of immersive scenes, digital humans and autonomous driving. 🔗:

Code dropped! Link in comment!

Join us for "Volumetric Video in the Real World", a tutorial on 4D research #CVPR2025 in Nashville, on Wednesday June 11 from 9am-5pm in Room 205B #CVPR2025 ! With amazing experts Aleksander Holynski Christian Richardt Boris Ivanovic Yiyi Liao Sharath Girish & Lan Xu 🔗nvlabs.github.io/cvpr2025-volum…

Going to be a great tutorial, see you all in Nashville on Wednesday!

Join our #CVPR2025 Tutorial on Volumetric Video in the Real World on 6/11! With amazing speakers: Aleksander Holynski Christian Richardt Boris Ivanovic Yiyi Liao Sharath Girish & Lan Xu ⏲️Wed, 6/11, 9am - 5pm CDT 🏢Room 205B, Music City Center, Nashville TN #CVPR2025 🔗nvlabs.github.io/cvpr2025-volum…

📣 Happening now! Our #cvpr2025 tutorial “Volumetric Video in the Real World”, in Room 205B Check the full schedule at nvlabs.github.io/cvpr2025-volum…

Happy to share our latest work on efficient sensor tokenization for end-to-end driving architectures! arxiv.org/abs/2506.12251 We introduce a novel way to tokenize multi-camera input for AV Transformers that is resolution- and camera-count-agnostic, yet geometry-aware 🧵👇

The recordings from the #CVPR2025 tutorial "Volumetric Video in the Real World" are now available! nvlabs.github.io/cvpr2025-volum…

Learned from in-the-wild images, GAIA generates 3D Gaussian animatable avatars with identity & expression control and real-time animation 📅 Talk: Aug 14, 9 AM PDT – West Bldg, Rm 211–214 🎮 Live demo @ poster session & E-Tech 🔗research.nvidia.com/labs/amri/proj… #SIGGRAPH2025 NVIDIA AI