时间：2026-04-23 14:30:002026-04-23 15:30:00
地点：均胜楼340
线上链接：750-877-849（腾讯会议）
主讲人：Prof. Yao Wang
主持人：曾文军 院士，讲席教授
讲座语言：
主办单位：信息学部
品牌栏目：
主讲人
Yao Wang is a Professor at New York University. She served as Associate/Vice Dean for Faculty Affairs for NYU Tandon from 2019 to 2025. Her research focuses on video coding and streaming, multimedia signal processing, computer vision, and medical imaging. She is the leading author of the textbook Video Processing and Communications. She is an IEEE Fellow. She received the IEEE Communications Society Leonard G. Abraham Prize Paper Award in the Field of Communications Systems in 2004, and the IEEE Communications Society Multimedia Communication Technical Committee Best Paper Award in 2011.
摘要
This talk will highlight recent research in the NYU Tandon Video Lab on deep learning for video streaming and health. The first part will focus on learning-based compression for point cloud video, a flexible 3D representation that enables free-viewpoint experiences in AR/VR applications. We begin by introducing a color compression scheme that generates a bitstream optimized for rendering quality, leveraging the 3D Gaussian Splatting (3DGS) representation. We then present a geometry coding method that uses a probabilistic surface element representation organized within an octree structure (pSurfelTree).
The second part will showcase AI-driven innovations in health applications. This includes work on decoding speech from intracranial neural signals, with the long-term goal of developing neuroprosthetics for individuals with speech impairments. We will also discuss interpretable, robust, and parameter-efficient learning frameworks that unroll optimization algorithms, with applications to MRI image denoising and reconstruction.
讲座海报
