amrita
@amritamaz
@nvidia research
The recordings from the #CVPR2025 tutorial "Volumetric Video in the Real World" are now available! nvlabs.github.io/cvpr2025-volum…
Join us for "Volumetric Video in the Real World", a tutorial on 4D research @CVPR in Nashville, on Wednesday June 11 from 9am-5pm in Room 205B #CVPR2025 ! With amazing experts @holynski_ @c_richardt @iamborisi @yiyi_liao_ @sharathgirish97 & Lan Xu 🔗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 🧵👇
📣 Happening now! Our #cvpr2025 tutorial “Volumetric Video in the Real World”, in Room 205B Check the full schedule at nvlabs.github.io/cvpr2025-volum…

Join our #CVPR2025 Tutorial on Volumetric Video in the Real World on 6/11! With amazing speakers: @holynski_ @c_richardt @iamborisi @yiyi_liao_ @sharathgirish97 & Lan Xu ⏲️Wed, 6/11, 9am - 5pm CDT 🏢Room 205B, Music City Center, Nashville TN @CVPR 🔗nvlabs.github.io/cvpr2025-volum…
Going to be a great tutorial, see you all in Nashville on Wednesday!
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!
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…
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. 🔗:…
Join us for "Volumetric Video in the Real World", a tutorial on 4D research @CVPR in Nashville, on Wednesday June 11 from 9am-5pm in Room 205B #CVPR2025 ! With amazing experts @holynski_ @c_richardt @iamborisi @yiyi_liao_ @sharathgirish97 & Lan Xu 🔗nvlabs.github.io/cvpr2025-volum…

📣 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!
Spatial AI is increasingly important, and the newest papers from #NVIDIAResearch, 3DGRT and 3DGUT, represent significant advancements in enabling researchers and developers to explore and innovate with 3D Gaussian Splatting techniques. 💎 3DGRT (Gaussian Ray Tracing) ➡️…
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
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
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
@amritamaz 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
👑 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 @sharathgirish97 @_TianyeLi @amritamaz @abhi2610 @davedotluebke @shalinidemello @NVIDIA @NVIDIAAI @UofMaryland
Excited to be @WiMLworkshop mentor tables, come join us!
1/4 We're thrilled to announce our incredible lineup of mentors! Join us on December 11 at 11 AM for a mentorship session where you'll have the chance to sit at a table with a mentor and six other participants to discuss anything you'd like.
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…