Graphics and multimedia - Microsoft Research

Publication

EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing

Kaizhi Zheng, Xiaotong Chen, Xuehai He, Jing Gu, Linjie Li, Zhengyuan Yang, K. Lin, Jianfeng Wang, Lijuan Wang, Xin Eric Wang, Linjie Li

ICLR 2025 | October 2024

Group

Interactive Multimodal Futures (IMF)

Interactive Multimodal Futures focuses on creating interactive systems and experiences that blend the richness and complexity of people and their real, physical world with advanced technology. We seek to leverage multimodal generative AI models that…

Project

ASL STEM Wiki

Dataset and Benchmark for Interpreting STEM Articles

Publication

CMMD: Contrastive Multi-Modal Diffusion for Video-Audio Conditional Modeling

Ruihan Yang, Hannes Gamper, Sebastian Braun

AVGenL: Audio-Visual Generation and Learning (workshop at ECCV 2024) | September 2024

Publication

Scribble: Auto-Generated 2D Avatars with Diverse and Inclusive Art-Direction

Lohit Petikam, Charlie Hewitt, Shideh Rezaeifar

SIGGRAPH | July 2024

Publication

GeoGen: Geometry-Aware Generative Modeling via Signed Distance Functions

Salvatore Esposito, Qingshan Xu, Kacper Kania, Charlie Hewitt, Octave Mariotti, Lohit Petikam, Julien Valentin, Arno Onken, Oisin Mac Aodha

Computer Vision and Pattern Recognition 2024 Workshops | June 2024

Tool

Kahani

“Kahani” is a research prototype that allows the user to create stories with visually striking and culturally nuanced images (visuals/scenes) just by describing them in their local languages. This web-based tool will also allow users…

Access

Podcast

What’s Your Story: Ivan Tashev

February 1, 2024

Partner Software Architect Ivan Tashev talks about applying his expertise in audio signal processing to the design and study of audio components for Microsoft products such as Kinect and shares how a focus on what…

Tool

LLMR

This repo contains the code described in LLMR (opens in new tab), implementing the Large Language Model for Mixed Reality framework. This package serves as a prototype for “Speaking the world into existence”, which allows the…

GitHub

Publication

COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design

Peidong Jia, Chenxuan Li, Yuhui Yuan, Zeyu Liu, Yichao Shen, Bohan Chen, Xingru Chen, Yinglin Zheng, Dong Chen, Ji Li, Xiaodong Xie, Shanghang Zhang, Baining Guo

November 2023