Graphics and multimedia - Microsoft Research

Publication

VoluMe – Authentic 3D Video Calls from Live Gaussian Splat Prediction

Marti de La Gorce, Charlie Hewitt, Tibor Takacs, Robert Gerdisch, Zafiirah Hosenie, Givi Meishvili, Marek Kowalski (HE/HIM), Tom Cashman, Antonio Criminisi

2025 International Conference on Computer Vision | October 2025

Video

Publication

DAViD: Data-efficient and Accurate Vision Models from Synthetic Data

Fatemeh Saleh, Sadegh Aliakbarian, Charlie Hewitt, Lohit Petikam, Xiao-Xian, Antonio Criminisi, Tom Cashman, Tadas Baltrusaitis

2025 International Conference on Computer Vision | October 2025

Video

Career Opportunity

Applied Scientist II – M365 Copilot Create ML team

Posted: September 4, 2025

Location: Noida, Uttar Pradesh, India

Research Area(s): Artificial intelligence, Graphics and multimedia

Are you an applied scientist with a passion for applying state-of-the-art AI innovations to augment human creativity? Join us as we grow the M365 Copilot Create ML team, where we are revolutionizing visual creation within the M365 Copilot, Microsoft Designer, Photos.…

Career Opportunity

Head of Applied Science – Clipchamp

Posted: August 30, 2025

Location: Adelaide, South Australia, Australia; Australia; Brisbane, Queensland, Australia; Melbourne, Victoria, Australia; Sydney, New South Wales, Australia

Research Area(s): Artificial intelligence, Graphics and multimedia

We’re seeking a Head of Applied Science to lead the future of AI-powered video creation and consumption. In this hands-on leadership role, you’ll set strategic direction, grow and mentor a team of high-performing scientists and…

Publication

RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination

Chong Zeng, Yue Dong, Pieter Peers, Hongzhi Wu, Xin Tong

SIGGRAPH 2025 | August 2025

Career Opportunity

Senior Applied Scientist – M365 Copilot Create ML team

Posted: July 10, 2025

Location: Bangalore, Karnataka, India; Noida, Uttar Pradesh, India

Research Area(s): Artificial intelligence, Graphics and multimedia

Are you an applied scientist with a passion for applying state-of-the-art AI innovations to augment human creativity? Join us as we grow the M365 Copilot Create ML team, where we are revolutionizing visual creation within the…

Video

Neural Representation Learning in the Wild: Toward Generalizable Representations and Scalable Citizen Science for Brain-Computer Interfaces

May 20, 2025 | Maurice Abou Jaoude, Chris Aimone , Jean-Michel Fournier, Aravind Ravi

This talk will explore how large-scale self-supervised learning, combined with our latest multimodal neurotechnology—the newly released Muse integrating EEG and functional near-infrared spectroscopy (fNIRS)—and an open citizen science platform, accelerates the development of robust and…

01:30:14

Microsoft Research Blog

VidTok introduces compact, efficient tokenization to enhance AI video processing

April 2, 2025 | Tianyu He, Junliang Guo, Jiang Bian

The VidTok method can enable AI systems to process and generate videos more effectively. Compact tokenization reduces computational costs while maintaining video quality across a potentially diverse set of applications.

Video

World and Human Action Models towards gameplay ideation (Supplementary Video 1)

March 3, 2025 | Linda Yilin Wen

Supplementary Video 1 provided with the article “World and Human Action Models towards gameplay ideation” (Kanervisto et al. 2025, https://www.nature.com/articles/s41586-025-08600-3 (opens in new tab)). We show video case studies of WHAM-generated gameplay sequences that demonstrate…

06:27

Video

WHAM Demonstrator tutorial

February 21, 2025 | Martin Greyson

Introducing Muse, our World and Human Action Model (WHAM). Muse is a generative AI model of a video game that can generate game visuals, controller actions, or both. It can predict how the game will…

18:59