About Me
I am a senior machine learning/computer vision engineer working on Apple RoomPlan/RoomPlan Enhancement and Vision Pro, from Video Engineering Group, Apple Inc. RoomPlan is a new Swift API, first released in WWDC22 that uses the camera and LiDAR Scanner on iPhone and iPad to create a 3D floor plan of a room. And in WWDC23, we enable RoomPlan with MultiRoom support and enhancements to room representation.
I am an experienced researcher with a variety of expertise in developing and delivering algorithm in generative AI, spatial computing, scene understanding and multimodal, with publications on 3D/2D generation, perception, videos, cameras, 3D vision and content generation. At Apple, I work closely with AIML for the research project. Previous, I worked at Snap Research and Palo Alto Research Center.
I received my Ph.D. from University of Maryland, College Park and was advised by Prof. Rama Chellappa. I received my M.S. degree from University of Maryland and B.S. degree in Electrical Engineering and Information Science from University of Science and Technology of China.
News
- Oct, 2023. Our paper “RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture” is accepted to ACM Multimedia 2023. [arXiv] [demo]. Congratulations to Liangchen Song, Liangliang Cao and all co-authors.
- Jun, 2023. RoomPlan Enhancement is released in Apple WWDC2023. In this year, we have enabled RoomPlan with lots of exciting and powerful features such as multi-room scanning, multi-room layout, object attributes, polygon walls, improved representation for furnitures, room-type and floor-shape.
- May, 2023. Our paper, “RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture” is online!
- Oct, 2022. Our research article, “3D Parametric Room Representation with RoomPlan” is published at Apple Machine Learning Research. Read our research article to learn more!
- Jun, 2022. RoomPlan is released in Apple WWDC2022. RoomPlan brings in the power of Apple LiDAR, state of the art 3D machine learning and an amazing scanning UI all in one place. Looking forward to seeing what developers will build with this incredible technology in areas such as interior design, architecture, real estate and E-commerce.