Skip to content
AI News HubLIVE
Original source2 min read

NIRJALA: Draining the Sea out of Gaussian Splatting with Three-Path Optics and Reversible Physics

Summary

NIRJALA introduces a three-path underwater image formation model with a range-saturating forward-scattering term and a reversible physics anchor, fixing unbounded inversion gain in Gaussian-splatting water removal and adding a 30-scene path-traced benchmark.

SourcearXiv Computer VisionAuthor: Latchan Chhetri, Aman Kumar
NIRJALA: Draining the Sea out of Gaussian Splatting with Three-Path Optics and Reversible Physics
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 17 Nov 2026]

Title:NIRJALA: Draining the Sea out of Gaussian Splatting with Three-Path Optics and Reversible Physics

View a PDF of the paper titled NIRJALA: Draining the Sea out of Gaussian Splatting with Three-Path Optics and Reversible Physics, by Latchan Chhetri and 1 other authors

View PDF HTML (experimental)

Abstract:Water does not just tint an underwater photograph; it rewrites it. Each pixel mixes attenuated scene radiance, backscattered light, and scene light scattered forward on its way to the camera, and many combinations of scene and water explain the same pixels. Most Gaussian-splatting methods for underwater scenes model only the first two effects and remove the water by dividing by a transmission that decays exponentially with range, so their inversion gain grows without bound. We present NIRJALA (Sanskrit for "without water"), a 3D Gaussian Splatting framework that recovers water-free appearance and geometry together. TRIVENI, a three-path image formation model, adds a range-saturating forward-scattering term to direct transmission and backscatter; we prove that this keeps the inversion gain bounded at every range and bound how errors in the estimated backscatter and attenuation propagate into the recovered colours. PRATIBIMBA, a reversible physics anchor, ties a flexible neural water model to a ten-parameter physical model in both directions, so scene content cannot hide inside the water. SAMARASA collects the physics-informed objectives, including a range-binned colour prior. To score water removal against ground truth, we built SAJALA ("with water"), a 30-scene suite path-traced in Blender Cycles with water-free images, depth, and normals under controlled water colour and turbidity. On SAJALA, NIRJALA raises PSNR from 24.34 to 24.76 dB and lowers depth AbsRel from 0.109 to 0.091 against the strongest baseline; on real SeaThru-NeRF scenes it lowers LPIPS from 0.194 to 0.175 while rendering at 44 FPS. We also discuss where appearance metrics and geometry disagree underwater, and the limits of our evaluation.

Comments: 21 pages, 11 figures

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)

Cite as: arXiv:2611.23450 [cs.CV]

(or arXiv:2611.23450v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.23450

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Latchan Chhetri [view email] [v1] Tue, 17 Nov 2026 19:53:32 UTC (6,827 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled NIRJALA: Draining the Sea out of Gaussian Splatting with Three-Path Optics and Reversible Physics, by Latchan Chhetri and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs cs.GR

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • The three-path model proves bounded inversion gain at all ranges and bounds how backscatter and attenuation errors propagate into recovered colors.
  • PRATIBIMBA ties a flexible neural water model to a ten-parameter physical model in both directions so scene content cannot hide inside the water.
  • On SAJALA, PSNR rises from 24.34 to 24.76 dB and depth AbsRel falls from 0.109 to 0.091; on real SeaThru-NeRF scenes LPIPS drops from 0.194 to 0.175 at 44 FPS.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

NIRJALA: Draining the Sea out of Gaussian Splatting with Three-Path Optics and Reversible Physics | AI News Hub