HDR-Net-Fusion:Real-time 3D dynamic scene reconstruction with a hierarchical deep reinforcement network
HDR-Net-Fusion: Real-time 3D dynamic scene reconstruction with a hierarchical deep reinforcement network作者机构:BNRistDepartment of Computer Science and TechnologyTsinghua UniversityBeiing 100084China Kuaishou Technology Co.Ltd.Beijing 100085China
出 版 物:《Computational Visual Media》 (计算可视媒体(英文版))
年 卷 期:2021年第7卷第4期
页 面:419-435页
核心收录:
学科分类:08[工学] 080203[工学-机械设计及理论] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术(可授工学、理学学位)]
主 题:dynamic 3D scene reconstruction deep reinforcement learning point cloud completion deep neural networks
摘 要:Reconstructing dynamic scenes with commodity depth cameras has many applications in computer graphics,computer vision,and ***,due to the presence of noise and erroneous observations from data capturing devices and the inherently ill-posed nature of non-rigid registration with insufficient information,traditional approaches often produce low-quality geometry with holes,bumps,and *** propose a novel 3D dynamic reconstruction system,named HDR-Net-Fusion,which learns to simultaneously reconstruct and refine the geometry on the fly with a sparse embedded deformation graph of surfels,using a hierarchical deep reinforcement(HDR)*** latter comprises two parts:a global HDR-Net which rapidly detects local regions with large geometric errors,and a local HDR-Net serving as a local patch refinement operator to promptly complete and enhance such *** the global HDR-Net is formulated as a novel reinforcement learning problem to implicitly learn the region selection strategy with the goal of improving the overall reconstruction *** applicability and efficiency of our approach are demonstrated using a large-scale dynamic reconstruction *** method can reconstruct geometry with higher quality than traditional methods.