Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Overall network structure.

More »

Fig 1 Expand

Fig 2.

Feature Enhancement Module.

More »

Fig 2 Expand

Fig 3.

Prior Processing Module.

More »

Fig 3 Expand

Fig 4.

Discriminator architecture based on self-attention.

More »

Fig 4 Expand

Fig 5.

Scale factor applied prior to softmax operation.

More »

Fig 5 Expand

Fig 6.

Normal estimation pipeline:

(a) Neighborhood selection for point p. (b) PCA-based normal computation (red arrows). (c) Local coordinate system construction.

More »

Fig 6 Expand

Fig 7.

Comparison of the effect of generating chair-like point clouds using different methods.

More »

Fig 7 Expand

Table 6.

Ablation Study on Keypoint Sampling Ratio for Curvature Estimation.

More »

Table 6 Expand

Table 1.

Experimental settings.

More »

Table 1 Expand

Table 2.

Quantitative comparison of point cloud data generated for chairs and airplanes.

More »

Table 2 Expand

Table 3.

Comparison of training, reasoning speed and model parameter quantity.

More »

Table 3 Expand

Fig 8.

Objective function variation curve of chair category point cloud generation process.

More »

Fig 8 Expand

Fig 9.

The generation process of point clouds for chair categories.

More »

Fig 9 Expand

Fig 10.

Generating the point cloud of aircraft categories.

More »

Fig 10 Expand

Table 4.

Classification and verification test.

More »

Table 4 Expand

Table 5.

Comparative Analysis of Normal Estimation Methods.

More »

Table 5 Expand

Table 7.

Generate ablation experiment results for two categories chairs and airplanes.

More »

Table 7 Expand

Table 8.

Quantitative comparison of other methods for modifying discriminators.

More »

Table 8 Expand