SemSegDepth: A Combined Model for Semantic Segmentation and Depth Completion

TL;DR

This paper introduces SemSegDepth, an end-to-end multi-task model that jointly performs semantic segmentation and depth completion, improving accuracy by leveraging shared features from RGB and sparse depth inputs.

Contribution

It presents a novel combined model architecture that integrates semantic segmentation and depth completion tasks into a single end-to-end framework, enhancing performance over independent approaches.

Findings

Joint training improves accuracy of both tasks.

Model outperforms separate task models on Virtual KITTI 2 dataset.

Multi-task approach enhances scene understanding capabilities.

Abstract

Holistic scene understanding is pivotal for the performance of autonomous machines. In this paper we propose a new end-to-end model for performing semantic segmentation and depth completion jointly. The vast majority of recent approaches have developed semantic segmentation and depth completion as independent tasks. Our approach relies on RGB and sparse depth as inputs to our model and produces a dense depth map and the corresponding semantic segmentation image. It consists of a feature extractor, a depth completion branch, a semantic segmentation branch and a joint branch which further processes semantic and depth information altogether. The experiments done on Virtual KITTI 2 dataset, demonstrate and provide further evidence, that combining both tasks, semantic segmentation and depth completion, in a multi-task network can effectively improve the performance of each task. Code is available at https://github.com/juanb09111/semantic depth.