In Defense of Classical Image Processing: Fast Depth Completion on the CPU

Abstract

With the rise of data driven deep neural networks as a realization of universal function approximators, most research on computer vision problems has moved away from hand crafted classical image processing algorithms. This paper shows that with a well designed algorithm, we are capable of outperforming neural network based methods on the task of depth completion. The proposed algorithm is simple and fast, runs on the CPU, and relies only on basic image processing operations to perform depth completion of sparse LIDAR depth data. We evaluate our algorithm on the challenging KITTI depth completion benchmark, and at the time of submission, our method ranks first on the KITTI test server among all published methods. Furthermore, our algorithm is data independent, requiring no training data to perform the task at hand. The code written in Python will be made publicly available at https://github.com/kujason/ip_basic.

References in corpus (5)

• End to End Learning for Self-Driving Cars
• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
• Pyramid Scene Parsing Network
• Joint 3D Proposal Generation and Object Detection from View Aggregation
• Multi-View 3D Object Detection Network for Autonomous Driving

Cited by in corpus (8)

• Confidence Propagation through CNNs for Guided Sparse Depth Regression
• Learning Guided Convolutional Network for Depth Completion
• ILabel: Interactive Neural Scene Labelling
• Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation
• CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion
• Robust and accurate depth estimation by fusing LiDAR and Stereo
• Dense Depth Posterior (DDP) from Single Image and Sparse Range
• Conf-Net: Toward High-Confidence Dense 3D Point-Cloud with Error-Map Prediction