ADAADepth: Adapting Data Augmentation and Attention for Self-Supervised Monocular Depth Estimation
- 30 July 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (4) , 7791-7798
Abstract
Self-supervised learning of depth has been a highly studied topic of research as it alleviates the requirement of having ground truth annotations for predicting depth. Depth is learnt as an intermediate solution to the task of view synthesis, utilising warped photometric consistency. Although it gives good results when trained using stereo data, the predicted depth is still sensitive to noise, illumination changes and specular reflections. Also, occlusion can be tackled better by learning depth from a single camera. We propose ADAA, utilising depth augmentation as depth supervision for learning accurate and robust depth. We propose a relational self-attention module that learns rich contextual features and further enhances depth results. We also optimize the auto-masking strategy across all losses by enforcing L1 regularisation over mask. Our novel progressive training strategy first learns depth at a lower resolution and then progresses to the original resolution with slight training. We utilise a ResNet18 encoder, learning features for prediction of both depth and pose. We evaluate our predicted depth on the standard KITTI driving dataset and achieve state-of-the-art results for monocular depth estimation whilst having significantly lower number of trainable parameters in our deep learning framework. We also evaluate our model on Make3D dataset showing better generalization than other methods.Keywords
All Related Versions
Funding Information
- Visvesvaraya PhD Scheme MeitY
This publication has 33 references indexed in Scilit:
- Unsupervised Monocular Depth Estimation with Left-Right Consistency2017
- Unsupervised Learning of Depth and Ego-Motion from Video2017
- Deeper Depth Prediction with Fully Convolutional Residual Networks2016
- Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue2016
- Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture2015
- Discrete-Continuous Depth Estimation from a Single Image2014
- Depth Transfer: Depth Extraction from Video Using Non-Parametric SamplingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Make3D: Learning 3D Scene Structure from a Single Still ImageIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004