Improved Classification-Based Monocular Depth Estimation for Robust Generalization of Diverse Scenes
Open Access
- 11 August 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (16) , 8003
Abstract
Recently, monocular depth estimation methods with neural networks trained using an image-depth database have become widely used and prevalent techniques. However, their generalization abilities are often constrained by training data: models trained on indoor datasets may perform well on other indoor datasets but exhibit some performance degradation for outdoor scenes. Therefore, developing a monocular depth estimation network with strong generalization capability for diverse scenes is challenging. In this paper, we propose a monocular depth estimation model that exhibits high generalizability and performs effectively across various scenarios without additional fine-tuning. In terms of model design, we adopt a powerful visual encoder to extract rich semantic features and incorporate the proposed multiple depth prediction heads with self-adaptability for robust depth estimation. With the designed modules and architectural refinements, the proposed model achieves a favorable balance between parameter efficiency and inference accuracy. After testing several unseen datasets, the simulation results demonstrate that the proposed method achieves better estimation performance than the baseline method and shows better robust visualization performance on multiple seen and unseen datasets.Keywords
Funding Information
- National Science and Technology Council, Taiwan (NSTC 114-2221-E-006-105)
This publication has 36 references indexed in Scilit:
- Exploring Inter-Domain Wasserstein Metric for Adaptive Object DetectionIEEE Transactions on Multimedia, 2026
- Mixed Layer Depth Estimation From Multisource Remote Sensing Data Using Clustering-Machine Learning MethodIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025
- Camera Based AI Models Used with LiDAR Data for Improvement of Detected Object Parameters2024
- BinsFormer: Revisiting Adaptive Bins for Monocular Depth EstimationIEEE Transactions on Image Processing, 2024
- Accurate light field depth estimation under occlusionPattern Recognition, 2023
- 3D point cloud data processing with machine learning for construction and infrastructure applications: A comprehensive reviewAdvanced Engineering Informatics, 2022
- Estimating Depth From Monocular Images as Classification Using Deep Fully Convolutional Residual NetworksIEEE Transactions on Circuits and Systems for Video Technology, 2017
- Obtaining depth map from segment-based stereo matching using graph cutsJournal of Visual Communication and Image Representation, 2011
- A state of the art in structured light patterns for surface profilometryPattern Recognition, 2010
- Solid-state time-of-flight range cameraIEEE Journal of Quantum Electronics, 2001