Neptune-Net: Wavelet and segmentation priors for monocular depth estimation in underwater scenes

Recovering geometrically coherent depth from underwater images is difficult because attenuation and scattering weaken local appearance cues and obscure object boundaries. We propose Neptune-Net, a dual-stream network that couples frequency-aware depth representations with segmentation-derived structural priors. A wavelet-based encoder–decoder retains low-frequency surface structure and directional detail across feature resolutions. A frozen EfficientSAM encoder supplies object-related context, which guides adaptive feature refinement through spatially varying residual modulation. This mechanism integrates structural information while preserving a depth-specific feature pathway, and an adaptive-bin head converts the refined representation into continuous depth predictions. Input wavelet enhancement and training-only WaterCut further address low contrast and local detail loss without altering depth supervision. Experiments on FLSea and USOD10K yield absolute relative errors of 0.1100 and 0.5150, respectively, with boundary F-scores of 0.1400 and 0.3800 at a two-pixel tolerance. On FLSea, Neptune-Net reduces absolute relative error by 28.57% relative to a controlled EfficientNet-B5/adaptive-bin baseline with the same input processing. Component ablations support the complementary contributions of wavelet processing, segmentation-conditioned refinement and input adaptation. These results demonstrate the effectiveness of coupling local frequency information with structural context for underwater monocular depth estimation.

Authors

Publication Details

Journal
Results in Engineering
Published
2026-11-16
DOI
https://doi.org/10.1016/j.rineng.2026.114057
Primary Topic
Advanced Vision and Imaging
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Neptune-Net: Wavelet and segmentation priors for monocular depth estimation in underwater scenes

Tao Liu, Bo Pang, Peiliang Li, Gang Xu
5 links
Results in Engineering
Advanced Vision and Imaging
article

Neptune-Net: Wavelet and segmentation priors for monocular depth estimation in underwater scenes

Tao Liu, Bo Pang, Peiliang Li, Gang Xu
article en

Abstract

Recovering geometrically coherent depth from underwater images is difficult because attenuation and scattering weaken local appearance cues and obscure object boundaries. We propose Neptune-Net, a dual-stream network that couples frequency-aware depth representations with segmentation-derived structural priors. A wavelet-based encoder–decoder retains low-frequency surface structure and directional detail across feature resolutions. A frozen EfficientSAM encoder supplies object-related context, which guides adaptive feature refinement through spatially varying residual modulation. This mechanism integrates structural information while preserving a depth-specific feature pathway, and an adaptive-bin head converts the refined representation into continuous depth predictions. Input wavelet enhancement and training-only WaterCut further address low contrast and local detail loss without altering depth supervision. Experiments on FLSea and USOD10K yield absolute relative errors of 0.1100 and 0.5150, respectively, with boundary F-scores of 0.1400 and 0.3800 at a two-pixel tolerance. On FLSea, Neptune-Net reduces absolute relative error by 28.57% relative to a controlled EfficientNet-B5/adaptive-bin baseline with the same input processing. Component ablations support the complementary contributions of wavelet processing, segmentation-conditioned refinement and input adaptation. These results demonstrate the effectiveness of coupling local frequency information with structural context for underwater monocular depth estimation.

Results in EngineeringVol. 32
National Natural Science Foundation of China
Life below water
Advanced Vision and Imaging
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon