WaterMono: Teacher-Guided Anomaly Masking and Enhancement Boosting for Robust Underwater Self-Supervised Monocular Depth Estimation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910495164858368 |
|---|---|
| author | Ding, Yilin Li, Kunqian Mei, Han Liu, Shuaixin Hou, Guojia |
| author_facet | Ding, Yilin Li, Kunqian Mei, Han Liu, Shuaixin Hou, Guojia |
| contents | Depth information serves as a crucial prerequisite for various visual tasks, whether on land or underwater. Recently, self-supervised methods have achieved remarkable performance on several terrestrial benchmarks despite the absence of depth annotations. However, in more challenging underwater scenarios, they encounter numerous brand-new obstacles such as the influence of marine life and degradation of underwater images, which break the assumption of a static scene and bring low-quality images, respectively. Besides, the camera angles of underwater images are more diverse. Fortunately, we have discovered that knowledge distillation presents a promising approach for tackling these challenges. In this paper, we propose WaterMono, a novel framework for depth estimation coupled with image enhancement. It incorporates the following key measures: (1) We present a Teacher-Guided Anomaly Mask to identify dynamic regions within the images; (2) We employ depth information combined with the Underwater Image Formation Model to generate enhanced images, which in turn contribute to the depth estimation task; and (3) We utilize a rotated distillation strategy to enhance the model's rotational robustness. Comprehensive experiments demonstrate the effectiveness of our proposed method for both depth estimation and image enhancement. The source code and pre-trained models are available on the project home page: https://github.com/OUCVisionGroup/WaterMono. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13344 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WaterMono: Teacher-Guided Anomaly Masking and Enhancement Boosting for Robust Underwater Self-Supervised Monocular Depth Estimation Ding, Yilin Li, Kunqian Mei, Han Liu, Shuaixin Hou, Guojia Computer Vision and Pattern Recognition Depth information serves as a crucial prerequisite for various visual tasks, whether on land or underwater. Recently, self-supervised methods have achieved remarkable performance on several terrestrial benchmarks despite the absence of depth annotations. However, in more challenging underwater scenarios, they encounter numerous brand-new obstacles such as the influence of marine life and degradation of underwater images, which break the assumption of a static scene and bring low-quality images, respectively. Besides, the camera angles of underwater images are more diverse. Fortunately, we have discovered that knowledge distillation presents a promising approach for tackling these challenges. In this paper, we propose WaterMono, a novel framework for depth estimation coupled with image enhancement. It incorporates the following key measures: (1) We present a Teacher-Guided Anomaly Mask to identify dynamic regions within the images; (2) We employ depth information combined with the Underwater Image Formation Model to generate enhanced images, which in turn contribute to the depth estimation task; and (3) We utilize a rotated distillation strategy to enhance the model's rotational robustness. Comprehensive experiments demonstrate the effectiveness of our proposed method for both depth estimation and image enhancement. The source code and pre-trained models are available on the project home page: https://github.com/OUCVisionGroup/WaterMono. |
| title | WaterMono: Teacher-Guided Anomaly Masking and Enhancement Boosting for Robust Underwater Self-Supervised Monocular Depth Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.13344 |