AI Paper Atlas

Research map / 3D vision / Depth and stereo

Self-supervised Monocular Underwater Depth Recovery, Image Restoration, and a Real-sea Video Dataset

Nisha Varghese, Ashish Kumar, A. N. Rajagopalan

ICCV 2023 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 40 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add view-synthesis loss on input hazy images (ablation)USe-ReDI-Net · SQUID depthPearson rho: 0.38 -> 0.55Improved
add view-synthesis loss on enhanced images (ablation)USe-ReDI-Net · SQUID depthPearson rho: 0.31 -> 0.55Improved
add geometry cue (view-synthesis) on top of haze cue (ablation)USe-ReDI-Net · SQUID depthPearson rho: 0.18 -> 0.55Improved
add Beta-Net and channel-wise depth consistency loss (ablation)USe-ReDI-Net · UIEB restorationPSNR: 17.4 -> 18.9Improved
add view-synthesis losses (geometry) to reconstruction loss (ablation)USe-ReDI-Net · UIEB restorationPSNR: 17.2 -> 18.9Improved
use joint disentanglement with view synthesis versus UW-Net (3.5 sec) for depth speedUSe-ReDI-Net · 512x512 imageexecution time: 3.5 sec -> 18msImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy