Depth-Independent Depth Completion via Least Square Estimation
This work addresses depth completion for computer vision applications, but it is incremental as it builds on existing methods with a two-stage approach.
The paper tackles depth completion by proposing a least square-based method that decouples neural networks from sparse depth inputs, enabling robust performance under varying sparsity and producing high-quality super-resolution depth maps. Experiments show competitive results on benchmarks.
The depth completion task aims to complete a per-pixel dense depth map from a sparse depth map. In this paper, we propose an efficient least square based depth-independent method to complete the sparse depth map utilizing the RGB image and the sparse depth map in two independent stages. In this way can we decouple the neural network and the sparse depth input, so that when some features of the sparse depth map change, such as the sparsity, our method can still produce a promising result. Moreover, due to the positional encoding and linear procession in our pipeline, we can easily produce a super-resolution dense depth map of high quality. We also test the generalization of our method on different datasets compared to some state-of-the-art algorithms. Experiments on the benchmark show that our method produces competitive performance.