Monocular Depth Estimation: A Review on Hybrid Architectures, Transformers and Addressing Adverse Weather Conditions
Monocular depth estimation is one of the essential tasks in computer vision as it can provide depth information from 2D images and is extremely beneficial for applications such as autonomous driving, robot navigation, etc. Monocular depth estimation has significantly improved over the past couple of...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2025-01-01
|
| Series: | Applied Computer Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/acss-2025-0003 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823860473049645056 |
|---|---|
| author | Kumara Lakindu Senanayake Nipuna Poravi Guhanathan |
| author_facet | Kumara Lakindu Senanayake Nipuna Poravi Guhanathan |
| author_sort | Kumara Lakindu |
| collection | DOAJ |
| description | Monocular depth estimation is one of the essential tasks in computer vision as it can provide depth information from 2D images and is extremely beneficial for applications such as autonomous driving, robot navigation, etc. Monocular depth estimation has significantly improved over the past couple of years and deep learning-based methods have surpassed traditional and machine learning-based methods. Deep learning-based methods have further been enhanced using transformer and hybrid approaches. This paper first discusses the sensors used for depth estimation and their limitations. Then, we briefly discuss the evolution of depth estimation. Then we dive into the deep learning methods including transformer and CNN-transformer hybrid methods and their limitations. Later, we discuss several methods addressing challenging weather conditions. Finally, we discuss the current trends, challenges and future directions of the transformer and hybrid methods. |
| format | Article |
| id | doaj-art-0b6173d7daca41a7987d4df69aad9fc8 |
| institution | Kabale University |
| issn | 2255-8691 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Applied Computer Systems |
| spelling | doaj-art-0b6173d7daca41a7987d4df69aad9fc82025-02-10T13:25:17ZengSciendoApplied Computer Systems2255-86912025-01-01301213310.2478/acss-2025-0003Monocular Depth Estimation: A Review on Hybrid Architectures, Transformers and Addressing Adverse Weather ConditionsKumara Lakindu0Senanayake Nipuna1Poravi Guhanathan2Informatics Institute of Technology, Colombo, Sri LankaInformatics Institute of Technology, Colombo, Sri LankaInformatics Institute of Technology, Colombo, Sri LankaMonocular depth estimation is one of the essential tasks in computer vision as it can provide depth information from 2D images and is extremely beneficial for applications such as autonomous driving, robot navigation, etc. Monocular depth estimation has significantly improved over the past couple of years and deep learning-based methods have surpassed traditional and machine learning-based methods. Deep learning-based methods have further been enhanced using transformer and hybrid approaches. This paper first discusses the sensors used for depth estimation and their limitations. Then, we briefly discuss the evolution of depth estimation. Then we dive into the deep learning methods including transformer and CNN-transformer hybrid methods and their limitations. Later, we discuss several methods addressing challenging weather conditions. Finally, we discuss the current trends, challenges and future directions of the transformer and hybrid methods.https://doi.org/10.2478/acss-2025-0003addressing weather conditionsattentioncnn-transformer hybrid methodsmonocular depth estimation |
| spellingShingle | Kumara Lakindu Senanayake Nipuna Poravi Guhanathan Monocular Depth Estimation: A Review on Hybrid Architectures, Transformers and Addressing Adverse Weather Conditions Applied Computer Systems addressing weather conditions attention cnn-transformer hybrid methods monocular depth estimation |
| title | Monocular Depth Estimation: A Review on Hybrid Architectures, Transformers and Addressing Adverse Weather Conditions |
| title_full | Monocular Depth Estimation: A Review on Hybrid Architectures, Transformers and Addressing Adverse Weather Conditions |
| title_fullStr | Monocular Depth Estimation: A Review on Hybrid Architectures, Transformers and Addressing Adverse Weather Conditions |
| title_full_unstemmed | Monocular Depth Estimation: A Review on Hybrid Architectures, Transformers and Addressing Adverse Weather Conditions |
| title_short | Monocular Depth Estimation: A Review on Hybrid Architectures, Transformers and Addressing Adverse Weather Conditions |
| title_sort | monocular depth estimation a review on hybrid architectures transformers and addressing adverse weather conditions |
| topic | addressing weather conditions attention cnn-transformer hybrid methods monocular depth estimation |
| url | https://doi.org/10.2478/acss-2025-0003 |
| work_keys_str_mv | AT kumaralakindu monoculardepthestimationareviewonhybridarchitecturestransformersandaddressingadverseweatherconditions AT senanayakenipuna monoculardepthestimationareviewonhybridarchitecturestransformersandaddressingadverseweatherconditions AT poraviguhanathan monoculardepthestimationareviewonhybridarchitecturestransformersandaddressingadverseweatherconditions |