您的位置:首页 > 科学研究 > 学术科研

计信院前沿学术报告(2019.7.24)

发布时间:2019-07-12 来源:本站原创 作者:本站编辑   浏览次数:

报告题目:RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion

时间:2019年7月24日(星期三)上午9:00-10:00

地点:西南大学计算机与信息科学学院1314会议室

报告人:刘宇,阿德莱德大学 博士

报告人简介:

刘宇,现为阿德莱德大学博士,师从澳洲科学院院士 Ian Reid 教授。2013和2016分别在西南大学软件工程专业、浙江大学CAD&CG国家重点实验室获学士、硕士学位。2015年硕士期间曾访问美国南加州大学,师从奥斯卡科技成就奖获得者Paul Debevec教授。研究兴趣包括计算机视觉和深度学习,尤其是物体检测,视频分割,多物体跟踪,三维重建等。

内容摘要:

RGB images differentiate from depth images as they carry more details about the color and texture information, which can be utilized as a vital complementary to depth for boosting the performance of 3D semantic scene completion (SSC). SSC is composed of 3D shape completion (SC) and semantic scene labeling while most of the existing methods use depth as the sole input which causes the performance bottleneck. Moreover, the state-of-the-art methods employ 3D CNNs which have cumbersome networks and tremendous parameters. We introduce a light-weight Dimensional Decomposition Residual network (DDR) for 3D dense prediction tasks. The novel factorized convolution layer is effective for reducing the network parameters, and the proposed multi-scale fusion mechanism for depth and color image can improve the completion and segmentation accuracy simultaneously. Our method demonstrates excellent performance on two public datasets. Compared with the latest method SSCNet, we achieve 5.9% gains in SC-IoU and 5.7% gains in SSC-IOU, albeit with only 21% network parameters and 16.6% FLOPs employed compared with that of SSCNet.