Real Time Dense Depth Estimation by Fusing Stereo with Sparse Depth Measurements

TL;DR

This paper introduces a real-time depth estimation method that combines dense stereo images with sparse LIDAR or range camera measurements, improving accuracy efficiently.

Contribution

It proposes a novel fusion technique that integrates stereo and sparse depth data using anisotropic diffusion and semi-global matching, achieving real-time performance.

Findings

Significant accuracy improvements with limited sparse measurements

Runs at 5Hz on NVIDIA TX-2 for high-resolution images

Effective fusion of stereo and sparse depth data

Abstract

We present an approach to depth estimation that fuses information from a stereo pair with sparse range measurements derived from a LIDAR sensor or a range camera. The goal of this work is to exploit the complementary strengths of the two sensor modalities, the accurate but sparse range measurements and the ambiguous but dense stereo information. These two sources are effectively and efficiently fused by combining ideas from anisotropic diffusion and semi-global matching. We evaluate our approach on the KITTI 2015 and Middlebury 2014 datasets, using randomly sampled ground truth range measurements as our sparse depth input. We achieve significant performance improvements with a small fraction of range measurements on both datasets. We also provide qualitative results from our platform using the PMDTec Monstar sensor. Our entire pipeline runs on an NVIDIA TX-2 platform at 5Hz on 1280x1024 stereo images with 128 disparity levels.