大家好 真是好久不见！

随着夏天悄悄地靠近

我们新学期的工作也在火热进行中~

本学期第一次讲座来袭啦

让我们一起看看本次讲座的内容吧

When Depth Estimation Meets

 Deep Learning

   时间：4月20日 16:20  

地点：南实验楼E403

孙文秀:商汤科技研究院 研究副总监

本科毕业于南京大学电子科学与工程系，博士毕业于香港科技大学电子与计算机工程系。本科期间曾参加intel嵌入式邀请赛，获得国家一等奖。博士期间去日本国际情报学研究所（NII）进行短期研究访问。研究兴趣包括计算机视觉和像素级图像视频处理，发表计算机视觉顶级会议及期刊30多篇。

2015年加入商汤，现任商汤科技研究副总监，负责计算摄影算法解决方案、深度与运动感知的新技术研究，主要产品输出在手机行业。

Depth data is indispensable for reconstructing or understanding 3D scenes. It serves as a key ingredient for applications such as synthetic defocus, autonomous driving, and augmented reality.

 Although active 3D sensors (e.g., Lidar, ToF, and structured-light 3D scanner) can be employed, retrieving depth from monocular/stereo cameras is typically a more cost-effective approach. 

However, estimating depth from images is inherently under-determined, to regularize the problem, one typically needs handcrafted models characterizing the properties of depth data or scene geometry.

 As the recent advances in deep learning, depth estimation is cast as a learning task, leading to state-of-the-art performance. In this talk, I will present our new progress on depth estimation with convolutional neural networks (CNN). 

Particularly, I will first introduce cascade residual learning (CRL), our two-stage deep architecture on stereo matching producing high-quality disparity estimates. Observations with CRL inspires us to propose a domain-adaptation approach---zoom and learn (ZOLE)---for training a deep stereo matching algorithm without the ground-truth data of a target domain. 

By combining a view synthesis network and the first stage of CRL, we propose single view stereo matching (SVS) for single image depth estimation, with a performance superior to the classic stereo block matching method taking two images as inputs. 

Finally, I will present our endeavours when applying our core techniques to the depth-of-field effects on dual-lens smart phones.

扫一扫下图二维码 / 点击阅读原文 

即可报名参加讲座