西蒙弗雷泽大学(Simon Fraser University)Furukawa教授2017年11月01日VALSE Webinar 成功举办.
Yasutaka Furukawa is an assistant professor of Computing Science at Simon Fraser University. He is also a principal research scientist at Zillow Group. Prior to SFU, he was an assistant professor at Washington University in St. Louis. Before WUSTL, he was a software engineer at Google. Before Google, he was a post-doctoral research associate at University of Washington. He worked with Prof. Seitz and Prof. Curless at University of Washington, and Rick Szeliski at Facebook (was at Microsoft Research). He completed his Ph.D. under the supervision of Prof. Ponce at Computer Science Department of University of Illinois at Urbana-Champaign in May 2008.
Furukawa教授Webinar的题目为:Geometric priors in 3D modeling.
Prof. Furukawa presents a sequence of research that exploits geometric regularities for reconstructing high-quality 3D models from raw imaging sensor data. The classes of geometric priors range from low level geometric primitives such as lines, planes, or cuboids to high-level scene grammars constraining the reconstruction process.
问答部分:
问题1:So what you do is to transform the 3D point cloud into structured models? Do you use dense image matching in this workflow again?
回答:这个取决于应用,对于室内的很多应用,可以直接采用kinect这类深度传感器获得三维点云,进而转换成三维模型。对于室内的远距离应用,深度传感器往往距离有限,这时候还得依赖于从图像中恢复三维结构。此外,对室外的大部分应用来说,也是采用图像恢复结构的模式比较多。
问题2:I have read some papers about using the AI to calc the depth of Images. How do you think of it? Will the AI makes a big change to the MVS?
回答:这是一个很好地问题,在很多场合都有人问到这个类似的问题。其实有不少人尝试用深度学习方法来做MVS,但到目前为止,基本都失败了。用深度学习来估计深度的工作,目前已经有了一些进展。我个人比较倾向于认为深度学习有可能对MVS的工作有帮助。
问题3:If the rooftop of building in satellite image is occluded part by trees or shadows, is it still possible to infer the complete 3D model?
回答:这是可以的。我们可以推断出遮挡区域的信息,重建出完整的三维模型。
问题4:Do you think the techniques of procedural modeling for trees and buildings have no room to improve ?
回答:我认为用procedural modeling虽然研究了有一段时间了,但是用于做树木和建筑物的建模还有很大的发展空间。我们现在已经找到了几个很好的点并且正在开展相关研究,后续将可以看到我们在这个方向的论文。
录像视频在线观看地址: http://www.iqiyi.com/u/2289191062
活动参与方式:
1、VALSE Webinar活动全部网上依托VALSE QQ群的“群视频”功能在线进行,活动时讲者会上传PPT或共享屏幕,听众可以看到Slides,听到讲者的语音,并通过文字或语音与讲者交互;
2、为参加活动,需加入VALSE QQ群,目前A、B、C、D、E、F群已满,除讲者等嘉宾外,只能申请加入VALSE G群,群号:669280237。申请加入时需验证姓名、单位和身份,缺一不可。入群后,请实名,姓名身份单位。身份:学校及科研单位人员T;企业研发I;博士D;硕士M
3、为参加活动,请下载安装Windows QQ最新版,群视频不支持非Windows的系统,如Mac,Linux等,手机QQ可以听语音,但不能看视频slides;
4、在活动开始前10分钟左右,主持人会开启群视频,并发送邀请各群群友加入的链接,参加者直接点击进入即可;
5、活动过程中,请勿送花、棒棒糖等道具,也不要说无关话语,以免影响活动正常进行;
6、活动过程中,如出现听不到或看不到视频等问题,建议退出再重新进入,一般都能解决问题;
7、建议务必在速度较快的网络上参加活动,优先采用有线网络连接。