SemSegDepth: A Combined Model for Semantic Segmentation and Depth Completion
This work addresses the need for integrated scene understanding in autonomous systems, though it is incremental as it builds on existing multi-task approaches.
The paper tackles the problem of holistic scene understanding for autonomous machines by proposing an end-to-end model that jointly performs semantic segmentation and depth completion, using RGB and sparse depth inputs to produce dense depth maps and semantic segmentation images, with experiments on the Virtual KITTI 2 dataset showing improved performance for both tasks.
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.