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

TL;DR

This paper demonstrates that a simple, classical image processing algorithm can outperform neural network methods in depth completion tasks, running efficiently on CPU without training data, and achieves top results on the KITTI benchmark.

Contribution

The authors introduce a fast, CPU-based depth completion algorithm using basic image processing, outperforming neural network approaches and eliminating the need for training data.

Findings

Ranks first on KITTI depth completion benchmark

Runs efficiently on CPU with no training required

Outperforms neural network-based methods in accuracy

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.