標(biāo)題：Parametric Neural Operator for Non-Line-of-Sight Imaging
報(bào)告時(shí)間：2025年8月1日（星期五）16：00-17：00
報(bào)告地點(diǎn)：人民大街校區(qū)數(shù)學(xué)與統(tǒng)計(jì)學(xué)院415教室
主講人：段玉萍
主辦單位：數(shù)學(xué)與統(tǒng)計(jì)學(xué)院
報(bào)告內(nèi)容簡(jiǎn)介：
Non-line-of-sight (NLOS) imaging is an advanced computational imaging technology aimed at reconstructing obscured or hidden scenes using indirect light signals. These signals are typically generated through multiple reflections or scattering, resulting in weak signal strength and susceptibility to noise interference. Therefore, incorporating physical processes into the reconstruction is crucial for enhancing the quality. We propose a parametric neural operator model capable of learning complex mapping relationships. Through training, this model can simulate the propagation of light and extract useful information from indirect light signals. By leveraging the powerful fitting capabilities of neural networks, this approach can handle complex light transmission models and effectively reduce noise.
主講人簡(jiǎn)介：
段玉萍，2012年在新加坡南洋理工大學(xué)取得計(jì)算數(shù)學(xué)博士學(xué)位，2012年-2015年在新加坡科技研究資訊通信研究院擔(dān)任研究科學(xué)家。2016年任天津大學(xué)應(yīng)用數(shù)學(xué)中心教授，博士生導(dǎo)師，2023年加入北京師范大學(xué)數(shù)學(xué)科學(xué)學(xué)院。主要研究方向包括變分圖像處理方法和模型驅(qū)動(dòng)的深度學(xué)習(xí)方法，已在IEEE TPAMI、TIP、TMI、IP、JSC等期刊和CVPR、MICCAI等會(huì)議發(fā)表論文70余篇，已授權(quán)國(guó)際/國(guó)內(nèi)專(zhuān)利5項(xiàng)。
