多层次感知的多视图三维模型重建  

Multi-View 3D Model Reconstruction Based on Multi-Level Perception

作　　者：白静[1,2] 徐昊 BAI Jing;XU Hao(School of Computer Science and Engineering,North Minzu University,Yinchuan 750021,China;The Key Laboratory of Images&Graphics Intelligent Processing of State Ethnic Affairs Commission,Yinchuan 750021,China)

机构地区：[1]北方民族大学计算机科学与工程学院,银川750021 [2]国家民委图形图像智能处理实验室,银川750021

出　　处：《计算机工程与应用》2023年第2期232-239,共8页Computer Engineering and Applications

基　　金：国家自然科学基金(61762003,61972121);中国科学院“西部之光”人才培养引进计划(JF2012c016-2);宁夏优秀人才支持计划。

摘　　要：针对基于体素表征的多视图三维模型重建过程中,存在二维视图所包含的空间信息离散,空间网格中体素分布稀疏的问题,提出基于多层次感知的多视图三维模型重建方法,旨在通过对视图级、体素级与物体级信息的多层次感知,重建具有完整结构与局部细节的三维模型。在视图特征提取阶段设计了上下文感知的通道注意力模块来最大限度获取二维视图中潜在空间信息;在三维模型生成阶段,通过体素感知的VoxFocal Loss来促进空间网格中体素生成;在三维模型细化阶段,通过具有物体感知能力的三维判别器来自适应地消除三维模型中冗余体素,生成更具真实感的三维模型。在大型合成数据集ShapeNet和真实世界数据集Pix3D上验证了该方法的有效性与先进性。The multi-view 3D model reconstruction task based on voxel representation has the problem of discrete spatial information contained in the 2D view and sparse voxel distribution in the spatial grid.To solve the above problems,a multi-view 3D model reconstruction method based on multi-level perception is proposed.Through the multi-level perception of view-level,voxel-level and object-level information,a 3D model with complete structure and local details can be reconstructed.In the view feature extraction stage,the context-aware channel attention module is designed to maximize the potential spatial information in the 2D view.In the 3D model generation stage,the voxel-aware VoxFocal Loss is used to promote voxel generation in the spatial grid.In the 3D model refinement stage,the object-aware 3D discriminator is used to adaptively eliminate redundant voxels in the 3D model to make it more realistic.The effectiveness and advancement of this method have been verified on the large-scale synthetic dataset ShapeNet and the real-world dataset Pix3D.

关 键 词：三维重建 多层次感知 体素表征 注意力模块 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]