Underwater object detection improved by restoring degraded images after transmission
TERA: Task-Evidence Restoration for Underwater Object Detection under Bandwidth-Constrained Transmission
Computer Vision and Pattern Recognition
Summary
Detecting objects underwater is harder after images are shrunk and compressed to save data bandwidth when sending them. The authors created a dataset called AquaTX to test this problem with different compression methods. They propose TERA, a way to fix images and their features on the receiving end without changing the existing detector. Their method improves detection accuracy considerably on tested datasets and keeps performance high even with new compression types. This work shows it helps to think about how images are sent when building underwater detection systems.
What this means in practice
- •For marine robotics teams: Improve underwater object detection accuracy on bandwidth-limited communication by restoring images after compression without retraining detectors.
- •For underwater monitoring operators: Maintain reliable object detection performance during live underwater video transmission over limited networks by applying task-aware image restoration at the receiver.
Authors
Heejin Kim, Joon-Seok Song, Eunil Park
Abstract
Underwater object detectors are typically evaluated on pre-transmission images, overlooking additional degradation from bandwidth-constrained downscaling and compression. We introduce AquaTX, a controlled benchmark built from real underwater detection datasets with seen and held-out codecs. We also propose TERA, a metadata-blind receiver-side framework combining task-guided pixel restoration and dual-state feature correction while keeping the detector frozen. Under seen compound degradation, TERA improves mean average precision (mAP50:95, averaged over IoU thresholds from 0.50 to 0.95) from 37.7 to 50.0 on DUO-TX and from 31.5 to 41.3 on RUOD-TX relative to the frozen detector without restoration. TERA also preserves clean-input performance and remains competitive with detector fine-tuning under the held-out AVIF codec. These findings support transmission-aware evaluation and task-guided restoration for underwater object detection. Code is available at https://github.com/hijinkim/TERA.