Maria Shugrina

Maria Shugrina

Auto-generated profile, based on publicly available information

Maria Shugrina

Nvidia, Toronto, Canada

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 July 2024
Verified
Conference Paper
Open access
AHAnita Hu
Anita Hu
NDNishkrit Desai
Nishkrit Desai
HAHassan Abu Alhaija
Hassan Abu Alhaija
SKSeung Wook Kim
Seung Wook Kim
MSMaria Shugrina
Maria Shugrina
We present a technique that leverages 2D generative diffusion models (DMs) for interactive texture painting on the surface of 3D meshes. Unlike existing texture painting systems, our method allows artists to paint with any complex image texture, and in contrast with traditional texture synthesis, our brush not only generates seamless strokes in real-time, but can inpaint realistic transitions between different textures. To enable this application, we present a stamp-based method that applies an adapted pre-trained DM to inpaint patches in local render space, which is then projected into the texture image, allowing artists control over brush stroke shape and texture orientation. We further present a way to adapt the inference of a pre-trained DM to ensure stable texture brush identity, while allowing the DM to hallucinate infinite variations of the source texture. Our method is the first to use DMs for interactive texture painting, and we hope it will inspire work on applying generative models to highly interactive artist-driven workflows. Code and data for this paper are at github.com/nv-tlabs/DiffusionTexturePainting.

23 July 2023
Verified
Conference Paper
Open access
HAHassan Abu Alhaija
Hassan Abu Alhaija
JLJames Lucas
James Lucas
AZAlexander Zook
Alexander Zook
MBMichael Babcock
Michael Babcock
DTDavid Tyner
David Tyner
MSMaria Shugrina
Maria Shugrina
We present an AI-based tool for interactive material generation within the NVIDIA Omniverse environment. Our approach leverages a State-of-the-art Latent Diffusion model with some notable modifications to adapt it to the task of material generation. Specifically, we employ circular-padded convolution layers in place of standard convolution layers. This unique adaptation ensures the production of seamless tiling textures, as the circular padding facilitates seamless blending at image edges. Moreover, we extend the capabilities of our model by training additional decoders to generate various material properties such as surface normals, roughness, and ambient occlusions. Each decoder utilizes the same latent tensor generated by the de-noising UNet to produce a specific material channel. Furthermore, to enhance real-time performance and user interactivity, we optimize our model using NVIDIA TensorRT, resulting in improved inference speed for an efficient and responsive tool.

12 December 2023
Verified
Conference Paper
Open access
AHAnita Hu
Anita Hu
NDNishkrit Desai
Nishkrit Desai
AGAshley Goldstein
Ashley Goldstein
HAHassan Abu Alhaija
Hassan Abu Alhaija
SKSeung Wook Kim
Seung Wook Kim
MSMaria Shugrina
Maria Shugrina


17 May 2023 in IEEE Computer Graphics and Applications
Verified
Journal Article
Closed access
MSMaria Shugrina
Maria Shugrina
With artificial intelligence (AI) poised to transform the nature of creative media, it is especially important to design tools with the creative process in mind. While ample research demonstrates the importance of flow, playfulness, and exploration for creative tasks, these concepts are rarely considered when designing digital interfaces. My thesis develops principles for the design of intelligent and playful user interfaces through a series of concrete design tasks. I explore a number of approaches for establishing artist needs, develop digital representations that are amenable to both machine learning and user interaction, and design novel digital media that amplify, not stifle, creativity. I conclude with an informal design philosophy developed throughout this study and thoughts on how we can leverage AI to elevate human creativity.

19 July 2026
Verified
Conference Paper
Open access
CTClement Fuji Tsang
Clement Fuji Tsang
VMVismay Modi
Vismay Modi
MSMaria Shugrina
Maria Shugrina
We introduce a novel capture-to-simulation pipeline for in-the-wild 3D Gaussian Splat scenes, showing our research-based solutions for segmenting objects, predicting their volumetric mechanical properties using a recent learning-based method, and mixed splat-mesh physics simulations, all supported by recent features in the Kaolin Library. In this hands-on lab, attendees will follow along from their laptop, running Python apps and notebooks in the web browser while compute-heavy AI inference and simulation are performed on reserved cloud GPU back ends. By the end of the course, attendees will be able to use our latest tools to select, process, and simulate objects in a 3D captured scene, and will understand the basics of the segmentation, material assignment, and physics simulation methods that make this pipeline possible.