Delving Into Multi-Illumination Monocular Depth Estimation: A New Dataset and Method
- 12 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 1018-1032
Abstract
Monocular depth prediction has received significant attention in recent years. However, the impact of illumination variations, which can shift scenes to unseen domains, has often been overlooked. To address this, we introduce the first indoor scene dataset featuring RGB-D images captured under multiple illumination conditions, allowing for a comprehensive exploration of indoor depth prediction. Additionally, we propose a novel method, MI-Transformer, which leverages global illumination understanding through large receptive fields to capture depth-attention contexts. This enables our network to overcome local window limitations and effectively mitigate the influence of changing illumination conditions. To evaluate the performance and robustness, we conduct extensive qualitative and quantitative analyses on both the proposed dataset and existing benchmarks, comparing our method with state-of-the-art approaches. The experimental results demonstrate the superiority of our method across various metrics, making it the first solution to achieve robust monocular depth estimation under diverse illumination conditions. We provide the codes, pre-trained models, and dataset openly accessible at https://github.com/ViktorLiang/midepth .Keywords
Funding Information
- National Natural Science Foundation of China (61972162)
- Natural Science Foundation of Guangdong Province (2021A1515012625, 2021A1515011849)
- Guangdong Natural Science Funds for Distinguished Young Scholar (2023B1515020097)
- Singapore Ministry of Education Academic Research Fund Tier 1 (MSS23C002)
This publication has 58 references indexed in Scilit:
- DepthFormer: Exploiting Long-range Correlation and Local Information for Accurate Monocular Depth EstimationMachine Intelligence Research, 2023
- Single-View View Synthesis with Self-rectified Pseudo-StereoInternational Journal of Computer Vision, 2023
- Guiding Monocular Depth Estimation Using Depth-Attention Volume2020
- Learning Single-Image 3D Reconstruction by Generative Modelling of Shape, Pose and ShadingInternational Journal of Computer Vision, 2019
- Monocular depth estimation with hierarchical fusion of dilated CNNs and soft-weighted-sum inferencePattern Recognition, 2018
- Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Indoor Segmentation and Support Inference from RGBD Images2012
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence AlgorithmsInternational Journal of Computer Vision, 2002