GAMES Webinar 2017-03期 | Deep 3D Representation Learning for Visual Computing-UCSD-苏昊
【GAMES Webinar 2017-03期】
报告嘉宾：Hao Su (苏昊)，UCSD (加州大学圣地亚哥分校)
报告题目：Deep 3D Representation Learning for Visual Computing
Among all digital representations we have for real physical objects, 3D is arguably the most expressive encoding. 3D representations allow storage and manipulation of high-level information (e.g. semantics, affordances, function) as well as low-level features (e.g. appearance, materials) about the object. Exploiting this 3D structure promises to improve our ability to build machines and autonomous agents that sense, understand, and act on the physical world around us. Historically, 3D visual computing has predominantly focused on single 3D models or small model collections. Now, however, with the advent of large 3D repositories of object models and inexpensive 3D scanning, the opportunity arises to re-define the field from the perspective of 3D big data.
In this talk, I will overview the recent progress on deep learning methods for analyzing and synthesizing 3D data and introduce my work on this topic. Different from 2D images that have a dominant representation as arrays, 3D geometric data have multiple popular representations, ranging from point cloud, meshes, volumetric field to multi-view images, each fitting their own application scenarios. From a research point of view, each type of data format has its own properties that pose challenges to deep architecture design while also provide the opportunity for novel and efficient solutions. Under the guiding principle of learning representations from 3D big data, these approaches have led to novel learning architectures resulting in top-performing algorithms. I will conclude my talk by describing several promising directions for future research.
Hao Su has been in UC San Diego as Assistant Professor of Computer Science and Engineering since July, 2017. He is affiliated with the Contextual Robotis Institute and Center for Visual Computing. He served in the program committee of multiple conferences and workshops on computer vision, computer graphics, and machine learning. He is the program chair of 3DV’17, publication chair of 3DV’16, and chair of various workshops at CVPR, ECCV, and ICCV. He is also an invited speaker at NIPS’16 workshop, 3DV’16 workshop, and CVPR’17 tutorial on 3D deep learning.
Professor Su is interested in fundamental problems in broad disciplines related to artificial intelligence, including machine learning, computer vision, computer graphics, and robotics. He is particularly interested in deep learning for 3D data understanding and interconnecting 3D data with other modalities such as images and texts. Professor Su is leading the construction of ShapeNet, a large-scale 3D-centric knowledge base of objects, and used to work on ImageNet, a large-scale 2D image database. Applications of my research include robotics, autonomous driving, virtual/augmented reality, smart manufacturing, etc. He has published numerous papers in top conferences and journals in computer vision, computer graphics, machine learning, and social networks.