Monocular Depth Estimation for Autonomous Driving Based on Instance Clustering Guidance
Authors:
- 3 December 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
A novel monocular depth estimator for autonomous driving, which produces reliable instance depths via instance clustering guidance, is proposed in this work. First, we extract multi-scale feature maps from a road scene and initialize depth clusters. Second, we update the depth clusters using the feature maps through transposed cross-attention. To guide the update process, we develop the instance clustering membership (ICM) loss, which employs an instance segmentation map. Third, we transfer the updated depth clusters to the feature map at the finest resolution, from which we produce the final depth map. Extensive experimental results show that the proposed algorithm yields competitive results to state-of-the-art techniques on the KITTI, Cityscapes-DVPS, and SemKITTI-DVPS datasets.Keywords
This publication has 24 references indexed in Scilit:
- PolyphonicFormer: Unified Query Learning for Depth-Aware Video Panoptic Segmentation2022
- k-means Mask Transformer2022
- End-to-End Object Detection with Transformers2020
- The Edge of Depth: Explicit Constraints Between Segmentation and Depth2020
- Deep Ordinal Regression Network for Monocular Depth Estimation2018
- IM2CAD2017
- Unsupervised Monocular Depth Estimation with Left-Right Consistency2017
- Deep Residual Learning for Image Recognition2016
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012
- A Fuzzy Relative of the ISODATA Process and Its Use in Detecting Compact Well-Separated ClustersJournal of Cybernetics, 1973