Training Deep Networks for Real-world Computer Vision Scenarios with Rendered Data

使用渲染数据训练真实计算机视觉场景的深度网络

• 批准号: 401269959
• 负责人: Professor Dr.-Ing. Thomas Brox
• 金额: --
• 依托单位: Lehrstuhl für Mustererkennung und Bildverarbeitung (LMB)
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2018
• 资助国家: 德国
• 起止时间: 2017-12-31 至 2022-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/401269959?language=en
• 关键词: Training; Deep; Networks; Real; world

Approaching computer vision tasks with deep learning requires large datasets to exploit the full potential of this approach. For some computer vision tasks, such as motion estimation or depth estimation, however, it is impossible to provide such large datasets by manual annotation of images. One possible solution is the use of synthetic, rendered image data. In this case, both the input images and the desired outputs are rendered and are available for the training process. However, in the end, the network should provide good results on real data. In this project we want to develop methods that will allow us to train networks on synthetic data but also achieve optimal results on real data. To this end, we will develop methods that integrate non-annotated real data besides the annotated synthetic data into the training process. The focus will be on optical flow estimation and depth estimation from videos. Moreover, we want to investigate to what extent the developed concepts can be employed for image based control, too.

通过深度学习处理计算机视觉任务需要大量数据集才能充分发挥这种方法的潜力。然而，对于某些计算机视觉任务，例如运动估计或深度估计，不可能通过图像的手动注释来提供如此大的数据集。一种可能的解决方案是使用合成的渲染图像数据。在这种情况下，输入图像和所需的输出都会被渲染并可用于训练过程。然而，最终，网络应该在真实数据上提供良好的结果。在这个项目中，我们希望开发一些方法，使我们能够在合成数据上训练网络，同时在真实数据上获得最佳结果。为此，我们将开发将除带注释的合成数据之外的未带注释的真实数据集成到训练过程中的方法。重点是视频的光流估计和深度估计。此外，我们想研究所开发的概念在多大程度上也可以用于基于图像的控制。