Depth estimation features are helpful for 3D recognition. Commodity-grade depth cameras are able to capture depth and color image in real-time. However, glossy, transparent or distant surface cannot be scanned properly by the sensor. As a result, enhancement and restoration from sensing depth is an important task. Depth completion aims at filling the holes that sensors fail to detect, which is still a complex task for machine to learn. Traditional hand-tuned methods have reached their limits, while neural network based methods tend to copy and interpolate the output from surrounding depth values. This leads to blurred boundaries, and structures of the depth map are lost. Consequently, our main work is to design an end-to-end network improving completion depth maps while maintaining edge clarity. We utilize self-attention mechanism, previously used in image inpainting fields, to extract more useful information in each layer of convolution so that the complete depth map is enhanced. In addition, we propose boundary consistency concept to enhance the depth map quality and structure. Experimental results validate the effectiveness of our self-attention and boundary consistency schema, which outperforms previous state-of-the-art depth completion work on Matterport3D dataset. Our code is publicly available at https://github.com/tsunghan-wu/Depth-Completion.
翻译:深度估计功能有助于 3D 识别 3D 。 商品级深度摄像头能够实时捕捉深度和彩色图像 。 然而, 光滑、 透明或遥远的表面无法被传感器正确扫描 。 因此, 从感测深度的增强和恢复是一项重要任务 。 深度完成的目的是填补传感器无法探测的洞穴, 这仍然是机器学习的一项复杂任务 。 传统的手调方法已经达到极限, 而基于神经网络的方法往往复制和内插周围深度值的输出。 这导致边界模糊, 深度地图的结构也丢失 。 因此, 我们的主要工作是设计一个端对端网络, 改善完成深度图, 并同时保持边缘清晰度 。 我们使用先前用于图像绘制场的自我注意机制, 以提取每一层的有用信息, 从而强化完整的深度地图 。 此外, 我们提出了边界一致性概念, 以提高深度地图质量和结构。 实验结果验证了我们自我保存和边界一致性计划的有效性, 它比之前的状态/ 艺术深度完成深度地图 。 我们的MADMDMDMDMDMDR 可用的深度 。