Author Affiliations
1Liangjiang College of Artificial Intelligence, Chongqing University of Technology, Chongqing 401135, China2School of Computer Science and Engineering, Chongqing University of Technology, Chongqing 400054, Chinashow less
Fig. 1. Basic flow of algorithm
Fig. 2. Facial Makeup point cloud registration results. (a1) Initial pose of two point clouds; registration results of (b1) two point clouds under the classical ICP algorithm, (c1) 4D-ICP(Hue) algorithm, (d1) 4D-ICP (IAICP) algorithm,and (e1) proposed algorithm; (a2) initial pose of two point clouds; registration results of (b2) two point clouds under the classical ICP algorithm, (c2) 4D-ICP(Hue) algorithm, (d2) 4D-ICP (IAICP) algorithm, and (e2) proposed algorithm
Fig. 3. Kettle point cloud registration results. (a1) Initial pose of two point clouds; registration results of (b1) two point clouds under the classical ICP algorithm, (c1) 4D-ICP(Hue) algorithm, (d1) 4D-ICP (IAICP) algorithm,and (e1) proposed algorithm; (a2) initial pose of two point clouds; registration results of (b2) two point clouds under the classical ICP algorithm, (c2) 4D-ICP(Hue) algorithm, (d2) 4D-ICP (IAICP) algorithm, and (e2) proposed algorithm
Fig. 4. Plaster statue point cloud registration results. (a1) Initial pose of two point clouds; registration results of (b1) two point clouds under the classical ICP algorithm, (c1) 4D-ICP(Hue) algorithm, (d1) 4D-ICP (IAICP) algorithm, and (e1) proposed algorithm; (a2) initial pose of two point clouds; registration results of (b2) two point clouds under the classical ICP algorithm, (c2) 4D-ICP(Hue) algorithm, (d2) 4D-ICP (IAICP) algorithm, and (e2) proposed algorithm
Fig. 5. Time comparison line chart of registration results. (a) Time of each method on different models without noise; (b) time of each method on different models with Gaussian noise
Fig. 6. Error comparison line chart of registration results. (a) Error of each method on different models without noise; (b) error of each method on different models with Gaussian noise
Algorithm | Facial Makeup | Kettle | Plaster Statue |
---|
Time /s | RMSE | Time /s | RMSE | Time /s | RMSE |
---|
Classic ICP4DICP(Hue)4DICP(IAICP)Proposed | 41.95036.97447.46063.6731 | 0.75930.75930.73430.6285 | 161.083824.584625.05617.2946 | 1.03081.03081.01650.5526 | 403.943348.889252.532511.5577 | 1.77771.77771.77121.7538 |
|
Table 1. Comparison of registration results of four algorithms without noise
Algorithm | Facial Makeup | Kettle | Plaster Statue |
---|
Time /s | RMSE | Time /s | RMSE | Time /s | RMSE |
---|
Classic ICP4DICP(Hue)4DICP(IAICP)Proposed | 39.39518.25937.80494.1339 | 0.96981.21830.93160.6293 | 158.291434.657828.19508.3330 | 1.05841.10071.05820.5521 | 454.779659.026256.959612.0035 | 1.88171.82651.88111.7543 |
|
Table 2. Comparison of registration results of four algorithms with Gaussian noise