Laser & Optoelectronics Progress, Volume. 60, Issue 16, 1615009(2023)
Multi-View 3D Reconstruction Method Based on Self-Attention Mechanism
Fig. 1. Overall structure of SA-PatchmatchNet
Fig. 2. Internal structure of self-attention layer
Fig. 3. Learnable PatchmatchNet structure
Fig. 4. DTU dataset benchmark results. (a) Depth map; (b) confidence map; (c) point cloud result
Fig. 5. Relationship between the overall error and GPU memory and running time, the image size is 1152×864. (a) Relationship between overall error and GPU memory consumption; (b) relationship between overall error and running time
Fig. 6. Depth map comparison of ablation experiment. (a) Depth map without improvement; (b) improved depth map; (c) GT
Fig. 7. Point cloud local magnification comparison map in the ablation experiment
|
|
|
Get Citation
Copy Citation Text
Guangzhao Zhu, Bo Wei, Afeng Yang, Xin Xu. Multi-View 3D Reconstruction Method Based on Self-Attention Mechanism[J]. Laser & Optoelectronics Progress, 2023, 60(16): 1615009
Category: Machine Vision
Received: Oct. 8, 2022
Accepted: Nov. 24, 2022
Published Online: Aug. 18, 2023
The Author Email: Wei Bo (weibo@hdu.edu.cn)