1. 讲者介绍

王云龙：中国科学院自动化研究所，智能感知与计算研究中心，2019届博士毕业生。研究兴趣：计算成像、生物特征识别。

报告题目：The Art of Rays: Light Field Imaging and View Synthesis

报告摘要：自由空间中传播的光线携带着三维立体世界丰富的信息，是人类感知外部世界最重要的介质和载体之一。光场用来描述光线在自由空间中的分布，光场理论发展的同时，过去的二十余年间国内外各种各样的光场成像设备被研制和开发出来。微透镜型光场相机拍摄的光场图像记录了自由空间中光线的角度方向信息，是以牺牲空间位置采样率作为代价的。空间分辨率和角度分辨率互相制约的关系，是光场图像在计算机视觉任务中应用的瓶颈。为了突破这一瓶颈，本次报告基于光场成像理论，对光场视角合成技术进行探索和研究，介绍目前该领域最新的一些研究成果和我们自己的研究工作。

Spotlight：

深入浅出介绍光场成像；
带来在光场条件下利用深度学习完成生物特征识别任务的精彩分享；
来自即将毕业的师兄的独家心得感悟。

2. 讲者介绍

任民：中国科学院自动化研究所，智能感知与计算研究中心。研究兴趣：生物特征识别、计算机视觉。

报告题目：Deep Feature Representation for Iris

报告摘要：Iris recognition is a reliable personal identification method but there is still much room to improve its accuracy especially in less-constrained situations. For example, free movement of head pose may cause large rotation difference between iris images. And illumination variations may cause irregular distortion of iris texture. To match intra-class iris images with head rotation robustly, the existing solutions usually need a precise alignment operation by exhaustive search within a determined range in iris image preprosessing or brute-force searching the minimum Hamming distance in iris feature matching. In the wild environments, iris rotation is of much greater uncertainty than that in constrained situations and exhaustive search within a determined range is impracticable. We propose a unified feature-level solution to both alignment free and distortion robust iris recognition in the wild. A new deep learning based method named Alignment Free Iris Network (AFINet) is proposed, which utilizes a trainable VLAD (Vector of Locally Aggregated Descriptors) encoder called NetVLAD to decouple the correlations between local representations and their spatial positions. And deformable convolution is leveraged to overcome iris texture distortion by dense adaptive sampling.

Spotlight：