We use chamfer distance to compare two point clouds.
我们用 Chamfer distance 来比较两组点云。
During training, the model minimizes the chamfer distance between the predicted shape samples and the ground-truth points to improve reconstruction quality.
在训练过程中,模型通过最小化预测形状采样点与真实点之间的 Chamfer distance 来提升重建质量。
Barrow, H. G., Tenenbaum, J. M., Bolles, R. C., & Wolf, H. C. (1977). Parametric Correspondence and Chamfer Matching: Two New Techniques for Image Matching.(早期提出并推广 Chamfer matching/相关距离思想)
Borgefors, G. (1988). Hierarchical Chamfer Matching: A Parametric Edge Matching Algorithm.(经典的 Chamfer matching 论文)
Fan, H., Su, H., & Guibas, L. (2017). A Point Set Generation Network for 3D Object Reconstruction from a Single Image.(在点云生成/重建中使用 Chamfer distance 作为损失)
Groueix, T., et al. (2018). AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation.(生成模型中常用 Chamfer distance 评估与训练)