# Clean-GS: Semantic Mask-Guided Pruning for 3D Gaussian Splatting

Source: [Clean-GS: Semantic Mask-Guided Pruning for 3D Gaussian Splatting](<https://www.sota2.com/research/paper/695c96f453fdd5c36174357f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-07T05:00:04.581Z

Authors: Subhankar Mishra

Published: 2026-01-01T05:02:45.000Z

## Abstract

3D Gaussian Splatting produces high-quality scene reconstructions but generates hundreds of thousands of spurious Gaussians (floaters) scattered throughout the environment. These artifacts obscure objects of interest and inflate model sizes, hindering deployment in bandwidth-constrained applications. We present Clean-GS, a method for removing background clutter and floaters from 3DGS reconstructions using sparse semantic masks. Our approach combines whitelist-based spatial filtering with color-guided validation and outlier removal to achieve 60-80\\% model compression while preserving object quality. Unlike existing 3DGS pruning methods that rely on global importance metrics, Clean-GS uses semantic information from as few as 3 segmentation masks (1\\% of views) to identify and remove Gaussians not belonging to the target object. Our multi-stage approach consisting of (1) whitelist filtering via projection to masked regions, (2) depth-buffered color validation, and (3) neighbor-based outlier removal isolates monuments and objects from complex outdoor scenes. Experiments on Tanks and Temples show that Clean-GS reduces file sizes from 125MB to 47MB while maintaining rendering quality, making 3DGS models practical for web deployment and AR/VR applications. Our code is available at https://github.com/smlab-niser/clean-gs

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Scene Compression and Object Isolation on Temple 302 views, 3 masks](<https://www.sota2.com/research/sota/3d-scene-compression-and-object-isolation-on-temple-302-views-3-masks.md>): 3D Scene Compression and Object Isolation; Temple 302 views, 3 masks; Compression Rate (%): 62.4.

- [3D Scene Compression and Object Isolation on Isha 103 views, 103 masks](<https://www.sota2.com/research/sota/3d-scene-compression-and-object-isolation-on-isha-103-views-103-masks.md>): 3D Scene Compression and Object Isolation; Isha 103 views, 103 masks; Compression Rate: 80.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.00913>)

[PDF](<https://arxiv.org/pdf/2601.00913.pdf>)
