Depth Edge Guided CNNs for Sparse Depth Upsampling
This work addresses a domain-specific problem in computer vision for applications like 3D reconstruction, but it is incremental as it builds on existing neural network approaches with a novel guided layer.
The paper tackles the problem of upsampling sparse depth maps using color images as guidance, which often leads to artifacts like texture copy and depth blur. The proposed method uses a depth edge-guided convolutional layer to prevent depth values from crossing edges, achieving state-of-the-art performance on datasets like Virtual KITTI and Middlebury.
Guided sparse depth upsampling aims to upsample an irregularly sampled sparse depth map when an aligned high-resolution color image is given as guidance. Many neural networks have been designed for this task. However, they often ignore the structural difference between the depth and the color image, resulting in obvious artifacts such as texture copy and depth blur at the upsampling depth. Inspired by the normalized convolution operation, we propose a guided convolutional layer to recover dense depth from sparse and irregular depth image with an depth edge image as guidance. Our novel guided network can prevent the depth value from crossing the depth edge to facilitate upsampling. We further design a convolution network based on proposed convolutional layer to combine the advantages of different algorithms and achieve better performance. We conduct comprehensive experiments to verify our method on real-world indoor and synthetic outdoor datasets. Our method produces strong results. It outperforms state-of-the-art methods on the Virtual KITTI dataset and the Middlebury dataset. It also presents strong generalization capability under different 3D point densities, various lighting and weather conditions.