AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Underwater Visual SLAM with Depth Uncertainty and Medium Modeling

Rui Liu, Sheng Fan, Wenguan Wang, Yi Yang

ICCV 2025 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 9 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 underwater medium modeling (neural scattering field) to 3DGS mapping (ablation)DUV-SLAM · TartanAir-HardPSNR: 24.08 -> 27.57Improved
use separate attenuation and backscatter coefficients instead of a single shared one (ablation)DUV-SLAM · TartanAir-HardPSNR: 26.93 -> 27.57Improved
use separate attenuation and backscatter coefficients (ablation)DUV-SLAM · TartanAir-HardLPIPS/SSIM: SSIM 0.69 -> 0.67; LPIPS 0.29 -> 0.25Mixed
add Mahalanobis depth loss weighted by tracking uncertainty (LMD) (ablation)DUV-SLAM · TartanAir-HardPSNR: 25.60 -> 27.57Improved
add KL distribution loss LKL (ablation)DUV-SLAM · TartanAir-HardPSNR: 26.70 -> 27.57Improved
add all depth losses (LMD, LRGB-C, LKL) vs none (ablation)DUV-SLAM · FLSea Canyons-FlaPSNR: 23.77 -> 25.71Improved
add medium modeling to MonoGS and Photo-SLAM trackers (ablation)MonoGS, Photo-SLAM · FLSea Canyons-TCPSNR: Photo-SLAM 24.16 -> 26.07Improved
DUV-SLAM vs DROID-SLAM on tracking accuracyDUV-SLAM · TartanAir-Ocean EasyATE: 1.15 -> 1.26Hurt
DUV-SLAM uncertainty vs UncLe-SLAM uncertaintyDUV-SLAM · uncertainty AUSE averageAUSE: 0.25 -> 0.21Improved
DUV-SLAM on long sequencesDUV-SLAM · MIMIR-UW Ocean Floor t1-lATE (m): 15.59Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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