CAPDepth: 360 Monocular Depth Estimation by Content-Aware Projection
Solving the depth estimation problem in a 360° image space, which has holistic scene perception, has become a trend in recent years. However, depth estimation in common 360° images is prone to geometric distortion. Therefore, this study proposes a new method, CAPDepth, to address the geometric-disto...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/769 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589163496472576 |
|---|---|
| author | Xu Gao Yongqiang Shi Yaqian Zhao Yanan Wang Jin Wang Gang Wu |
| author_facet | Xu Gao Yongqiang Shi Yaqian Zhao Yanan Wang Jin Wang Gang Wu |
| author_sort | Xu Gao |
| collection | DOAJ |
| description | Solving the depth estimation problem in a 360° image space, which has holistic scene perception, has become a trend in recent years. However, depth estimation in common 360° images is prone to geometric distortion. Therefore, this study proposes a new method, CAPDepth, to address the geometric-distortion problem of 360° monocular depth estimation. We reduce the tangential projections by an optimized content-aware projection (CAP) and a geometric embedding module to capture more features for global depth consistency. Additionally, we adopt an index map and a de-blocking scheme to improve the inference efficiency and quality of our CAPDepth model. Our experiments show that CAPDepth greatly alleviates the distortion problem, producing smoother, more accurate predicted depth results, and improves performance in panoramic depth estimation. |
| format | Article |
| id | doaj-art-0b72d294dd134907b2262bdfed08b6c5 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-0b72d294dd134907b2262bdfed08b6c52025-01-24T13:20:45ZengMDPI AGApplied Sciences2076-34172025-01-0115276910.3390/app15020769CAPDepth: 360 Monocular Depth Estimation by Content-Aware ProjectionXu Gao0Yongqiang Shi1Yaqian Zhao2Yanan Wang3Jin Wang4Gang Wu5School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaCollege of Computer Science, Beijing University of Technology, Beijing 100124, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaSolving the depth estimation problem in a 360° image space, which has holistic scene perception, has become a trend in recent years. However, depth estimation in common 360° images is prone to geometric distortion. Therefore, this study proposes a new method, CAPDepth, to address the geometric-distortion problem of 360° monocular depth estimation. We reduce the tangential projections by an optimized content-aware projection (CAP) and a geometric embedding module to capture more features for global depth consistency. Additionally, we adopt an index map and a de-blocking scheme to improve the inference efficiency and quality of our CAPDepth model. Our experiments show that CAPDepth greatly alleviates the distortion problem, producing smoother, more accurate predicted depth results, and improves performance in panoramic depth estimation.https://www.mdpi.com/2076-3417/15/2/769depth estimationpanoramatransformergeometric distortionscontent-aware projectionfusion |
| spellingShingle | Xu Gao Yongqiang Shi Yaqian Zhao Yanan Wang Jin Wang Gang Wu CAPDepth: 360 Monocular Depth Estimation by Content-Aware Projection Applied Sciences depth estimation panorama transformer geometric distortions content-aware projection fusion |
| title | CAPDepth: 360 Monocular Depth Estimation by Content-Aware Projection |
| title_full | CAPDepth: 360 Monocular Depth Estimation by Content-Aware Projection |
| title_fullStr | CAPDepth: 360 Monocular Depth Estimation by Content-Aware Projection |
| title_full_unstemmed | CAPDepth: 360 Monocular Depth Estimation by Content-Aware Projection |
| title_short | CAPDepth: 360 Monocular Depth Estimation by Content-Aware Projection |
| title_sort | capdepth 360 monocular depth estimation by content aware projection |
| topic | depth estimation panorama transformer geometric distortions content-aware projection fusion |
| url | https://www.mdpi.com/2076-3417/15/2/769 |
| work_keys_str_mv | AT xugao capdepth360monoculardepthestimationbycontentawareprojection AT yongqiangshi capdepth360monoculardepthestimationbycontentawareprojection AT yaqianzhao capdepth360monoculardepthestimationbycontentawareprojection AT yananwang capdepth360monoculardepthestimationbycontentawareprojection AT jinwang capdepth360monoculardepthestimationbycontentawareprojection AT gangwu capdepth360monoculardepthestimationbycontentawareprojection |