# Multiple Prior Representation Learning for Self-Supervised Monocular Depth Estimation via Hybrid Transformer

arXiv: https://arxiv.org/abs/2406.08928 · HTML: https://mlsanity.com/paper/2406.08928/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 69 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [Co-Scale Conv-Attentional Image Transformers](https://mlsanity.com/paper/2104.06399/) (2021)
- [On the uncertainty of self-supervised monocular depth estimation](https://mlsanity.com/paper/2005.06209/) (2020)
- [Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance](https://mlsanity.com/paper/2007.06936/) (2020)
- [Feature-metric Loss for Self-supervised Learning of Depth and Egomotion](https://mlsanity.com/paper/2007.10603/) (2020)
- [MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer](https://mlsanity.com/paper/2208.03543/) (2022)
- [Improving Semantic Segmentation via Video Propagation and Label Relaxation](https://mlsanity.com/paper/1812.01593/) (2018)
- [Semantically-Guided Representation Learning for Self-Supervised Monocular Depth](https://mlsanity.com/paper/2002.12319/) (2020)
- [MPViT: Multi-Path Vision Transformer for Dense Prediction](https://mlsanity.com/paper/2112.11010/) (2021)
- [Context Prior for Scene Segmentation](https://mlsanity.com/paper/2004.01547/) (2020)
- [Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume](https://mlsanity.com/paper/2003.13951/) (2020)
- [HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2012.07356/) (2020)
- [Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2211.13202/) (2022)
- [Don't Forget The Past: Recurrent Depth Estimation from Monocular Video](https://mlsanity.com/paper/2001.02613/) (2020)
- [Model Complexity of Deep Learning: A Survey](https://mlsanity.com/paper/2103.05127/) (2021)
- [Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2112.13047/) (2021)

## Abstract (arXiv)

Self-supervised monocular depth estimation aims to infer depth information without relying on labeled data. However, the lack of labeled information poses a significant challenge to the model's representation, limiting its ability to capture the intricate details of the scene accurately. Prior information can potentially mitigate this issue, enhancing the model's understanding of scene structure and texture. Nevertheless, solely relying on a single type of prior information often falls short when dealing with complex scenes, necessitating improvements in generalization performance. To address these challenges, we introduce a novel self-supervised monocular depth estimation model that leverages multiple priors to bolster representation capabilities across spatial, context, and semantic dimensions. Specifically, we employ a hybrid transformer and a lightweight pose network to obtain long-range spatial priors in the spatial dimension. Then, the context prior attention is designed to improve generalization, particularly in complex structures or untextured areas. In addition, semantic priors are introduced by leveraging semantic boundary loss, and semantic prior attention is supplemented, further refining the semantic features extracted by the decoder. Experiments on three diverse datasets demonstrate the effectiveness of the proposed model. It integrates multiple priors to comprehensively enhance the representation ability, improving the accuracy and reliability of depth estimation. Codes are available at: urlhttps://github.com/MVME-HBUT/MPRLNet