SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.00913 · 2026

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

Subhankar Mishra

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
smlab-niser/clean-gs — 5 of 8
FunctionStatusWhere it lives
color_distance Ran smlab-niser/clean-gs/clean-gs.py
code served (permissive licence) · get_code("3e4803afea10e2f3")
load_cameras Ran smlab-niser/clean-gs/clean-gs.py
code served (permissive licence) · get_code("121894d7292adaaa")
process_view_color_validate Ran smlab-niser/clean-gs/clean-gs.py
code served (permissive licence) · get_code("37d4301a1ae72fb5")
process_view_whitelist Ran smlab-niser/clean-gs/clean-gs.py
code served (permissive licence) · get_code("35fe4fd13ff42d66")
sh_to_rgb Ran smlab-niser/clean-gs/clean-gs.py
code served (permissive licence) · get_code("f9255293c69be068")
Camera Not yet run smlab-niser/clean-gs/clean-gs.py
code served (permissive licence) · get_code("6bf87d8b88ecef01")
clean_gs Not yet run smlab-niser/clean-gs/clean-gs.py
code served (permissive licence) · get_code("576068a2cb4beb36")
project_gaussian_with_depth Not yet run smlab-niser/clean-gs/clean-gs.py
code served (permissive licence) · get_code("be3807ed77a72136")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2601.00913")
get_code_for_paper("2601.00913")
have("2601.00913")

Connect an agent — have() is free.