Graphics & multimedia - Microsoft Research

Publication

ε-VAE: Denoising as Visual Decoding

Long Zhao, Sanghyun Woo, Ziyu Wan, Yandong Li, Han Zhang, Boqing Gong, Hartwig Adam, Xuhui Jia, Ting Liu

ICML 2025 | February 2025

Publication

FlexiClip: Locality-Preserving Free-Form Character Animation

Anant Khandelwal

ICML 2025 | January 2025

Publication

GASP: Gaussian Avatars with Synthetic Priors

Jack Saunders, Charlie Hewitt, Yanan Jian, Marek Kowalski (HE/HIM), Tadas Baltrusaitis, Yiye Chen, Prof. Darren Cosker, Virginia Estellers, Nicholas Gyde, Vinay Namboodiri, Ben Lundell

Computer Vision and Pattern Recognition | January 2025

Video

GASP: Gaussian Avatars with Synthetic Priors

December 10, 2024

Gaussian Splatting has changed the game for real-time photo-realistic rendering. One of the most popular applications of Gaussian Splatting is to create animatable avatars, known as Gaussian Avatars. Recent works have pushed the boundaries of…

04:06

Publication

Computational Design of Dense Servers for Immersion Cooling

Milin Kodnongbua, Fiodar Kazhamiaka, Daniel S. Berger, Vikram Iyer, Alvin Lebeck, Rodrigo Fonseca, Ricardo Bianchini, Adriana Schulz

SIGGRAPH Asia & ACM Transactions on Graphics | December 2024

Publication

Eyelid Fold Consistency in Facial Modeling

Lohit Petikam, Charlie Hewitt, Fatemeh Saleh, Tadas Baltrusaitis

SIGGRAPH Asia | December 2024

Publication

Look Ma, no markers: holistic performance capture without the hassle

Charlie Hewitt, Fatemeh Saleh, Sadegh Aliakbarian, Lohit Petikam, Shideh Rezaeifar, Louis Florentin, Zafiirah Hosenie, Tom Cashman, Julien Valentin, Prof. Darren Cosker, Tadas Baltrusaitis

ACM Transactions on Graphics | December 2024, Vol 36(6): pp. 235:1-235:12

Video

Microsoft Research Blog

Research Focus: Week of November 11, 2024

November 13, 2024

Holistic motion-capture calibration technique without calibration, manual intervention or custom hardware; Research on AI agents for autonomous clouds; Automating proof-oriented program construction; One-to-many testing for natural language code generation.

Research Focus: Week of November 11, 2024

Publication

VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks

Lawrence Jang, Yinheng Li, Charles Ding, Justin Lin, Paul Pu Liang, Dan Zhao, Rogerio Bonatti, Kazuhito Koishida

ICLR 2025 | October 2024

Publication

SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending

Nels Numan, Shwetha Rajaram, Balasaravanan Thoravi Kumaravel, Nicolai Marquardt, Andrew D. Wilson

User Interface Software and Technology | October 2024