查看原文
其他

静5青年讲座 | Learning Dynamic 3D Objects from Images in the Wild

Learning Dynamic 3D Objects from Images in the Wild

报告人:Shangzhe Wu, University of Oxford

时间:2022年12月16日 星期五 10:00am

方式:腾讯会议 655 232 512(直播平台见文末)

Host:董豪 助理教授


 Abstract

We all live in a physical 3D world, full of dynamic 3D objects. Being able to perceive the dynamic world in 3D from 2D visual observations is not only key to many AR and robotics applications, but also fundamental to the goal of visual understanding. However, existing learning-based image understanding models often treat images simply as compositions of 2D patterns, ignoring the fact that they arise from a 3D world. The major obstacle is the lack of large-scale 3D data and annotations, which are typically required to train 3D perception systems but are prohibitively expensive to collect. Natural intelligences, on the other hand, develop a comprehensive 3D understanding of the world primarily by observing 2D projections, without relying on extensive 3D supervision. This begs the question that I attempt to answer in my research: "can machines learn to perceive the dynamic 3D world without explicit 3D supervision?" In this talk, I will present some of our recent efforts in approaching this question. In particular, I will show how we can learn disentangled, explicit 3D representations of objects from just raw online photos and videos through inverse rendering, without explicit 3D labels for training.


Biography

 


Shangzhe Wu is a PhD student in the Visual Geometry Group (VGG) at the University of Oxford, advised by Andrea Vedaldi and Christian Rupprecht. His current research focuses on unsupervised 3D learning and inverse rendering. He also spent time interning at Google Research with Noah Snavely's team. His work on unsupervised learning of symmetric 3D objects received the Best Paper Award at CVPR 2020. Homepage: https://elliottwu.com.


直播平台

↑↑蔻享学术↑↑

↑↑中心B站账号↑↑




往 期 讲 座



—   版权声明  —

本微信公众号所有内容,由北京大学前沿计算研究中心微信自身创作、收集的文字、图片和音视频资料,版权属北京大学前沿计算研究中心微信所有;从公开渠道收集、整理及授权转载的文字、图片和音视频资料,版权属原作者。本公众号内容原作者如不愿意在本号刊登内容,请及时通知本号,予以删除。

“阅读原文”查看海报

您可能也对以下帖子感兴趣

文章有问题?点此查看未经处理的缓存