基于先验知识的单视图三维点云重建算法研究  

Single-view 3D point cloud reconstruction algorithm based on priori knowledge

作　　者：陈雅丽 李海生[1,2,3] 王晓川 李楠 Chen Yali;Li Haisheng;Wang Xiaochuan;Li Nan(School of Computer&Engineering,Beijing Technology&Business University,Beijing 100048,China;Beijing Key Laboratory of Big Data Technology for Food Safety,Beijing 100048,China;National Engineering Laboratory for Agri-product Quality Traceability,Beijing 100048,China)

机构地区：[1]北京工商大学计算机学院,北京100048 [2]食品安全大数据技术北京市重点实验室,北京100048 [3]农产品质量安全追溯技术及应用国家工程实验室,北京100048

出　　处：《计算机应用研究》2023年第10期3168-3172,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(62277001);北京市自然科学基金—小米创新联合基金项目(L233026);北京市教委—市自然基金委联合资助项目(KZ202110011017)。

摘　　要：单幅图像的三维重建是一个不适定问题,由于图像与三维模型间存在的表示模式差异,通常存在物体自遮挡、低光照、多类对象等情况,针对目前单幅图像三维模型重建中重建模型具有歧义性的问题,提出了一种基于先验信息指导的多几何角度约束的三维点云模型重建方法。首先,通过预训练三维点云自编码器获得先验知识,并最小化输入图像特征向量与点云特征向量的差异,使得输入图像特征分布逼近点云特征分布;然后,利用可微投影模块将图像的三维点云表示形式从不同视角投影到二维平面;最后,通过最小化投影图与数据集中真实投影图的差异,优化初始重建点云。在ShapeNet和Pix3D数据集上与其他方法的定量定性比较结果表明了该方法的有效性。Single-view 3D reconstruction is an ill-posed problem.Due to the different modes of representation between the image and the 3D model,there are usually self-occlusion,low illumination,and multiple objects.Aiming at the ambiguity of the reconstructed model in the current 3D model reconstruction of a single image,this paper proposed a 3D point cloud model reconstruction method based on the guidance of prior information and multi-geometric angle constraints.Firstly,it obtained prior knowledge by pre-training the 3D point cloud encoder,and minimized the difference between the input image feature vector and the point cloud feature vector,so that the input image feature distribution approximated the point cloud feature distribution.Then,it used a differentiable projection module to project the three-dimensional point cloud representation of the image from different angles to a two-dimensional plane.Finally,it optimized the initial reconstructed point cloud by minimizing the diffe-rence between the projected image and the actual projected image in the dataset.The results of quantitative and qualitative comparison with other methods on ShapeNet and Pix3D datasets verify the effectiveness of the proposed algorithm.

关 键 词：点云 三维重建 深度学习 先验知识 可微投影模块 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]