Author Affiliations
Beijing Key Lab for Precision Optoelectronic Measurement Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, Chinashow less
Fig. 1. CSA module structure
Fig. 2. CA module structure
Fig. 3. SA module structure
Fig. 4. Overview of the CSA-PointNet++ structure
Fig. 5. Structure of the improved set abstraction module
Fig. 6. Kinect V2 camera. (a) Appearance; (b) internal structure
Fig. 7. Real-world self-constructed data. (a) Original point cloud data; (b) intercepted point cloud data
Fig. 8. Point cloud data after translational transformation
Fig. 9. Point cloud data after rotational transformation
Fig. 10. Part segmentation results
Method | ACC /% |
---|
MVCNN | 90.10 | VoxNet | 85.90 | PointNet | 90.32 | PointNet++ | 91.89 | DGCNN | 92.20 | PCT | 93.07 | Ours(r=4,4) | 93.20 | Ours(r=4,16) | 93.16 | Ours(r=16,16) | 93.10 | Ours(r=16,4) | 92.55 | Ours(without ReLU) | 92.56 |
|
Table 1. Classification results under ModelNet40 dataset (ACC)
Method | mIoU | airplane | bag | cap | car | chair | earphone | guitar | knife |
---|
PointNet | 79.87 | 81.73 | 77.28 | 87.18 | 75.01 | 90.24 | 73.54 | 90.81 | 86.05 | PointNet++ | 81.75 | 82.21 | 81.91 | 83.17 | 78.41 | 90.62 | 73.90 | 91.15 | 86.38 | DGCNN | 82.20 | 82.01 | 81.45 | 84.70 | 78.83 | 90.56 | 73.89 | 91.47 | 86.58 | PCT | 82.31 | | | | | | | | | Ours | 82.62 | 82.64 | 80.67 | 85.35 | 78.94 | 90.52 | 75.90 | 91.36 | 87.18 | Method | lamp | laptop | motorbike | mug | pistol | rocket | skateboard | table | | PointNet | 81.85 | 95.15 | 61.27 | 93.26 | 79.98 | 48.17 | 74.22 | 82.25 | | PointNet++ | 83.06 | 95.64 | 70.91 | 95.87 | 80.65 | 55.19 | 76.84 | 82.04 | | DGCNN | 83.81 | 95.70 | 70.37 | 94.97 | 81.15 | 61.53 | 76.56 | 81.65 | | PCT | | | | | | | | | | Ours | 84.08 | 95.63 | 71.33 | 95.43 | 82.06 | 61.91 | 76.61 | 82.29 | |
|
Table 2. Part segmentation results under ShapeNetPart dataset (IoU)
Method | ACC /% |
---|
PointNet++ | 91.89 | CA+PointNet++ | 92.93 | SA+PointNet++ | 92.99 | CSA+PointNet++ | 93.20 | SCA+PointNet++ | 92.20 |
|
Table 3. ACC of the ablation experiment
Method | mIoU /% |
---|
PointNet++ | 81.75 | CA+PointNet++ | 82.15 | SA+PointNet++ | 82.42 | CSA+PointNet++ | 82.62 | SCA+PointNet++ | 82.13 |
|
Table 4. Part segmentation results of the ablation experiment (mIoU)
Type | ACC /% |
---|
With ground | 52.81 | Without ground | 92.14 |
|
Table 5. ACC under the real-world self-constructed dataset
Translation | ACC /% |
---|
(x+1,y,z) | 90.96 | (x,y+1,z) | 91.85 | (x,y,z+1) | 90.85 | (x+1,y+1,z+1) | 91.70 |
|
Table 6. ACC of the translated real-world self-constructed dataset
Rotation | ACC /% |
---|
Rot_30° | 91.75 | Rot_60° | 89.59 | Rot_90° | 92.91 | Rot_120° | 90.99 | Rot_150° | 91.40 | Rot_180° | 90.59 | Rot_210° | 91.00 | Rot_240° | 90.01 | Rot_270° | 90.93 | Rot_300° | 91.37 | Rot_330° | 92.55 |
|
Table 7. ACC of the rotated real-world self-constructed dataset