Knowledge Distillation for Underwater Feature Extraction and Matching via GAN-synthesized Images

• URL: http://arxiv.org/abs/2504.08253v1
• Date: Fri, 11 Apr 2025 04:34:18 GMT
• Title: Knowledge Distillation for Underwater Feature Extraction and Matching via GAN-synthesized Images
• Authors: Jinghe Yang, Mingming Gong, Ye Pu,
• Abstract summary: In this paper, we aim to improve the robustness of the feature extraction and matching in the turbid underwater environment.<n>We first propose a novel adaptive GAN-synthesis method to estimate water parameters and underwater noise distribution.<n>We then introduce a general knowledge distillation framework compatible with different teacher models.
• Score: 40.403791826344275
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous Underwater Vehicles (AUVs) play a crucial role in underwater exploration. Vision-based methods offer cost-effective solutions for localization and mapping in the absence of conventional sensors like GPS and LIDAR. However, underwater environments present significant challenges for feature extraction and matching due to image blurring and noise caused by attenuation, scattering, and the interference of \textit{marine snow}. In this paper, we aim to improve the robustness of the feature extraction and matching in the turbid underwater environment using the cross-modal knowledge distillation method that transfers the in-air feature extraction models to underwater settings using synthetic underwater images as the medium. We first propose a novel adaptive GAN-synthesis method to estimate water parameters and underwater noise distribution, to generate environment-specific synthetic underwater images. We then introduce a general knowledge distillation framework compatible with different teacher models. The evaluation of GAN-based synthesis highlights the significance of the new components, i.e. GAN-synthesized noise and forward scattering, in the proposed model. Additionally, the downstream application of feature extraction and matching (VSLAM) on real underwater sequences validates the effectiveness of the transferred model.

Related papers

• Learning Underwater Active Perception in Simulation [51.205673783866146]
  Turbidity can jeopardise the whole mission as it may prevent correct visual documentation of the inspected structures. Previous works have introduced methods to adapt to turbidity and backscattering. We propose a simple yet efficient approach to enable high-quality image acquisition of assets in a broad range of water conditions.
  arXiv  Detail & Related papers  (2025-04-23T06:48:38Z)
• Phaseformer: Phase-based Attention Mechanism for Underwater Image Restoration and Beyond [25.975859029063585]
  We propose a lightweight phase-based transformer network with 1.77M parameters for underwater image restoration (UIR)<n>Our approach focuses on effectively extracting non-contaminated features using a phase-based self-attention mechanism.<n>We demonstrate its effectiveness for low-light image enhancement using the LOL dataset.
  arXiv  Detail & Related papers  (2024-12-02T12:48:19Z)
• FAFA: Frequency-Aware Flow-Aided Self-Supervision for Underwater Object Pose Estimation [65.01601309903971]
  We introduce FAFA, a Frequency-Aware Flow-Aided self-supervised framework for 6D pose estimation of unmanned underwater vehicles (UUVs) Our framework relies solely on the 3D model and RGB images, alleviating the need for any real pose annotations or other-modality data like depths. We evaluate the effectiveness of FAFA on common underwater object pose benchmarks and showcase significant performance improvements compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-09-25T03:54:01Z)
• UMono: Physical Model Informed Hybrid CNN-Transformer Framework for Underwater Monocular Depth Estimation [5.596432047035205]
  Underwater monocular depth estimation serves as the foundation for tasks such as 3D reconstruction of underwater scenes. Existing methods fail to consider the unique characteristics of underwater environments. In this paper, an end-to-end learning framework for underwater monocular depth estimation called UMono is presented.
  arXiv  Detail & Related papers  (2024-07-25T07:52:11Z)
• A deep learning approach for marine snow synthesis and removal [55.86191108738564]
  This paper proposes a novel method to reduce the marine snow interference using deep learning techniques. We first synthesize realistic marine snow samples by training a Generative Adversarial Network (GAN) model. We then train a U-Net model to perform marine snow removal as an image to image translation task.
  arXiv  Detail & Related papers  (2023-11-27T07:19:41Z)
• WaterFlow: Heuristic Normalizing Flow for Underwater Image Enhancement and Beyond [52.27796682972484]
  Existing underwater image enhancement methods mainly focus on image quality improvement, ignoring the effect on practice. We propose a normalizing flow for detection-driven underwater image enhancement, dubbed WaterFlow. Considering the differentiability and interpretability, we incorporate the prior into the data-driven mapping procedure.
  arXiv  Detail & Related papers  (2023-08-02T04:17:35Z)
• PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators [120.06891448820447]
  How to obtain clear and visually pleasant images has become a common concern of people. The task of underwater image enhancement (UIE) has also emerged as the times require. In this paper, we propose a physical model-guided GAN model for UIE, referred to as PUGAN. Our PUGAN outperforms state-of-the-art methods in both qualitative and quantitative metrics.
  arXiv  Detail & Related papers  (2023-06-15T07:41:12Z)
• DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge Distillation [44.99833362998488]
  We present DeepAqua, a self-supervised deep learning model that eliminates the need for manual annotations during the training phase. We exploit cases where optical- and radar-based water masks coincide, enabling the detection of both open and vegetated water surfaces. Experimental results show that DeepAqua outperforms other unsupervised methods by improving accuracy by 7%, Intersection Over Union by 27%, and F1 score by 14%.
  arXiv  Detail & Related papers  (2023-05-02T18:06:21Z)
• A Novel Underwater Image Enhancement and Improved Underwater Biological Detection Pipeline [8.326477369707122]
  This paper proposes a novel method for capturing feature information, which adds the convolutional block attention module (CBAM) to the YOLOv5 backbone. The interference of underwater creature characteristics on object characteristics is decreased, and the output of the backbone network to object information is enhanced.
  arXiv  Detail & Related papers  (2022-05-20T14:18:17Z)
• Single Underwater Image Enhancement Using an Analysis-Synthesis Network [21.866940227491146]
  Most deep models for underwater image enhancement resort to training on synthetic datasets based on underwater image formation models. A new underwater synthetic dataset is first established, in which a revised ambient light synthesis equation is embedded. A unified framework, named ANA-SYN, can effectively enhance underwater images under collaborations of priors and data information.
  arXiv  Detail & Related papers  (2021-08-20T06:29:12Z)
• Domain Adaptive Adversarial Learning Based on Physics Model Feedback for Underwater Image Enhancement [10.143025577499039]
  We propose a new robust adversarial learning framework via physics model based feedback control and domain adaptation mechanism for enhancing underwater images. A new method for simulating underwater-like training dataset from RGB-D data by underwater image formation model is proposed. Final enhanced results on synthetic and real underwater images demonstrate the superiority of the proposed method.
  arXiv  Detail & Related papers  (2020-02-20T07:50:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.