Masha Shugrina
@_shumash
Followers
356
Following
11
Media
16
Statuses
90
Senior Research Scientist at NVIDIA Toronto AI Lab. Manager of a subgroup focused on creative applications of AI and accelerating research. Opinions are my own.
Toronto
Joined March 2011
Proud to share great work by @rishit_dagli 🎉
📢want to produce realistic dynamic 3d worlds (with >100 splats) my new NVIDIA internship project, VoMP, is the first feed forward approach to convert input surface geometry to volumetric sim-ready assets by assigning real world physics materials 🌐Project:
0
0
4
See your Gaussian Splats deform and collide under gravity! #NVIDIA Kaolin Library just released v0.18.0. https://t.co/7Zv2YfHgmn Join us at #SIGGRAPH tomorrow Sunday, Aug 10, Room 121-122 for a hands-on lab showcasing this and an intro to NVIDIA Warp, used under the hood.
0
3
22
Join us Tuesday night at #SIGGRAPH2025 Real-Time Live show to see interactive painting with Gaussian splat brushes, awesome work (and technical paper) by Karran Pandey presented by him and our inspiring collaborators at the @thenfb!
Come watch not one, but TWO demos real time live 👀 Experience a new way to engage in Gaussian Splatting and how RTX Mega Geometry redefines GPU rendering at #SIGGRAPH2025 👉 https://t.co/1l83drlXmY
1
6
27
📢 GEN3C is now open-sourced, with code released under Apache 2.0 and model weights under the NVIDIA Open Model License! 🚀 Along with it, we're releasing a GUI tool that lets you specify your desired video trajectory in 3D — come play with it and generate your own! The
🚀Excited to introduce GEN3C #CVPR2025, a generative video model with an explicit 3D cache for precise camera control. 🎥It applies to multiple use cases, including single-view and sparse-view NVS🖼️ and challenging settings like monocular dynamic NVS and driving simulation🚗.
1
28
137
🚀 We just open-sourced Cosmos DiffusionRenderer! This major upgrade brings significantly improved video de-lighting and re-lighting—powered by NVIDIA Cosmos and enhanced data curation. Released under Apache 2.0 and Open Model License. Try it out! 🔗 https://t.co/h87zZhodp0
🚀 Introducing DiffusionRenderer, a neural rendering engine powered by video diffusion models. 🎥 Estimates high-quality geometry and materials from videos, synthesizes photorealistic light transport, enables relighting and material editing with realistic shadows and reflections
9
123
525
Curious about 3D Gaussians, simulation, rendering and the latest from #NVIDIA? Come to the NVIDIA Kaolin Library live-coding session at #CVPR2025, powered by a cloud GPU reserved especially for you. Wed, Jun 11, 8-noon. Bring your laptop! https://t.co/joCH5DDrNk
1
21
46
🚀 Introducing DiffusionRenderer, a neural rendering engine powered by video diffusion models. 🎥 Estimates high-quality geometry and materials from videos, synthesizes photorealistic light transport, enables relighting and material editing with realistic shadows and reflections
8
137
636
⚡ Ray Tracing + 3D Gaussians = New Possibilities! Gaussian splatting is limited by rasterization—our #SIGGRAPHAsia2024 paper shows how to ray trace instead, enabling reflections, shadows, fisheye cameras, and more. The most important (and hardest!) part is making it fast. (1/N)
8
106
697
Today at #SIGGRAPH. Hands-on lab, 2:15pm, Room 709. Dive Into #3D #DeepLearning #AI, #PhysicsSimulation, and Interactive 3D Prototyping With #NVIDIA Kaolin Library https://t.co/E8qUUDsNuN
0
0
6
Join hands-on lab at #SIGGRAPH to learn how to simulate points, 3D gaussian splats, meshes in just a few lines of code and right in your Jupyter notebook. So proud of the Kaolin Library team! 💚 https://t.co/PDg0Ra1GGs Or try today:
s2024.conference-program.org
The Premier Conference & Exhibition on Computer Graphics & Interactive Techniques. 51 years of SIGGRAPH and join us in Denver or online starting 28 July.
✨Just announced: Representation agnostics physics simulation. ➡️ https://t.co/hm6Bjev4pk This new framework is now available in the Kaolin Library. Simulate: ✅Gaussian Splats ✅Neural Radiance Fields ✅Signed Distance Functions and more…
0
5
21
If you want to simulate any point sampled geometry in just a few lines of code, this method is available in Kaolin Library pre-release version. Kudos @vm2358 & team. Check out:
(1/n) Happy to share that our paper, "Simplicits: Mesh-Free, Geometry-Agnostic, Elastic Simulations" will be presented at #SIGGRAPH2024
https://t.co/TxApBUNTcH
0
0
5
(1/n) Happy to share that our paper, "Simplicits: Mesh-Free, Geometry-Agnostic, Elastic Simulations" will be presented at #SIGGRAPH2024
https://t.co/TxApBUNTcH
7
26
95
Check out this convenience class for handling surface mesh tensor attributes. We hope it's useful and saves you at least some of the headache! #PyTorch #AI #deeplearning #3D
Exciting news for #PyTorch enthusiasts: Our NVIDIA Kaolin library introduces SurfaceMesh class to simplify managing mesh attributes including consistency, auto-compute normals, & streamline indexing. 👀 See the video tutorial from #NVIDIAResearch ➡️ https://t.co/2azNZZzIxH
1
5
22
So proud of my team for presenting the first interactive #texture #painting with #AI at #SIGGRAPHAsia2023 Real-Time Live. Well done Anita Hu and team!! We want the artist to stay in control 🎨🖌️🤗 https://t.co/vyy7eMKxwz
developer.nvidia.com
NVIDIA researchers took the stage at SIGGRAPH Asia Real-Time Live event in Sydney to showcase generative AI integrated into an interactive texture painting workflow, enabling artists to paint complex…
3
17
45
We are honored to have won Best Paper Awards 🏆 at #SIGGRAPHAsia2023 and #NeurIPS today. 🎉 We give hearty congratulations to all the research teams recognized at these events. 🧵 👇 1/3
3
26
191
🚀 Introducing our #SIGGRAPHAsia work “Adaptive Shells”, a novel #NeRF formulation that yields high visual fidelity and greatly accelerates rendering. TLDR: Auto-derived bounding shells result in up to 10x faster inference than InstantNGP! [1/n]
15
119
521
If you want to visualize 3D Gaussian Splatting radiance fields *interactively* in a Jupyter Notebook, here's an easy recipe using Kaolin Library: https://t.co/HctVc04z5V
1
15
85
Thank you @SIGGRAPH and Real-Time Live. We greatly appreciate the award for 🏆 Best in Show for #SIGGRAPH2023 for our Text2Materials demo by the #NVIDIAResearch team. 👀 See the demo: https://t.co/QHKl81dCph
3
36
108
Proud to announce latest #NVIDIA Kaolin library release, with lots of optimized pytorch utilities for 3D #DeepLearning .
📣 Just released: #NVIDIAKaolin v0.14.0 Accelerate 3D deep learning research, debug your custom renderer interactively in a Jupyter notebook, and manage batched mesh attributes with a SurfaceMesh container, within the Kaolin #Pytorch library. Github: https://t.co/b9hyI5yfyW
0
6
14