.png){kind=icon}
返回
Cascade Convolution Neural Network for Point Set Generation
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2021.3131775.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Automatic and efficient 3D object modeling has become critical in industrial applications. The advancement of deep convolutional neural networks (CNNs) has prompted researchers to use CNNs for learning 3D geometry information directly from images. However, the feature maps directly extracted by CNNs are more suitable for image processing tasks because they contain more deep texture information of the entire 2D image. Compared with this, 3D reconstruction tasks using CNNs demand geometric information about a specific object. The existing architecture mainly tries to infer the geometric structure through texture information, which leads to an uneven distribution of points in the generated point cloud object. To address this problem, we propose a cascade point set generation network (CPSGN) that deforms the predicted object while more effectively inferring the object's 3D geometric information from the 2D image so that the distribution of the final object becomes more uniform and denser. The CPSGN consists of a point set generation part for producing a basic 3D object and a point deformation part for fine-tuning the basic 3D object. In addition, we designed a projection loss that optimizes the geometry of the model by measuring shape differences from multiple perspectives. Experimental results on different benchmark datasets indicate that the produced point-based model outperforms existing approaches.
Keyword:
Three-dimensional displays
Feature extraction
Point cloud compression
Shape
Image reconstruction
Convolution
Strain
3D reconstruction
point cloud
CNN
point-based model
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Lösliche
trans
‐Di‐1‐alkinyl‐ und Poly‐
trans
‐ethinyl(tetraalkylphthalocyaninato)metall‐IVB‐DerivateLösliche
trans
-二-1-炔基-与聚-
trans
-乙炔基 (四烷基酞菁) 金属-ⅳ-衍生物
PREAI
分享收藏Investigation of Ti mesh-supported anodes for direct borohydride fuel cells直接硼氢化物燃料电池用钛网支撑阳极的研究
PREAI
分享收藏A Facile Synthesis of 4-Substituted Fluorenes by the Use of a Positional Protective Group.png)
Synthesis
SynthesisIF0
PREAI
分享收藏分享收藏Halloysite nanotube microspheres connected to an electrospun nanofiber membrane for effective and riskless hemostasis埃洛石纳米管微球连接到电纺纳米纤维膜，可有效且无风险地止血
PREAI
分享收藏
查看更多内容