arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.12919cs.CVcs.GRcs.LG
收藏

从合成环境中学习密集对应

Learning Dense Correspondence from Synthetic Environments

Mithun Lal, Anthony Paproki, Nariman Habili, Lars Petersson, Olivier Salvado, Clinton Fookes

摘要:

从单幅图像中估计人体的形状和姿态是一项具有挑战性的任务。将识别的人体形状映射到3D人体模型上是一个更加困难的问题。现有方法将真实2D图像中手动标记的人类像素映射到3D表面上,这容易出现人为错误,并且可用注释数据的稀疏性通常导致次优结果。我们建议通过使用自动生成的合成数据训练2D-3D人体映射算法来解决数据稀缺的问题,其中精确和密集的2D-3D对应关系是已知的。这种使用合成环境的学习策略对现实世界的数据具有很高的泛化潜力。使用不同的相机参数变化,背景和照明设置,我们创建了精确的地面实况数据,构成了更广泛的分布。我们使用COCO数据集和验证框架评估了在合成上训练的模型的性能。结果表明,在合成数据上训练2D-3D映射网络模型是使用真实数据的可行替代方案。

英文摘要:

Estimation of human shape and pose from a single image is a challenging task. It is an even more difficult problem to map the identified human shape onto a 3D human model. Existing methods map manually labelled human pixels in real 2D images onto the 3D surface, which is prone to human error, and the sparsity of available annotated data often leads to sub-optimal results. We propose to solve the problem of data scarcity by training 2D-3D human mapping algorithms using automatically generated synthetic data for which exact and dense 2D-3D correspondence is known. Such a learning strategy using synthetic environments has a high generalisation potential towards real-world data. Using different camera parameter variations, background and lighting settings, we created precise ground truth data that constitutes a wider distribution. We evaluate the performance of models trained on synthetic using the COCO dataset and validation framework. Results show that training 2D-3D mapping network models on synthetic data is a viable alternative to using real data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑