AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Geometry-Aware Style Transfer in 3D Gaussian Splatting

Min Hyeok Bang, Jun Hyeong Kim, Seung-Wook Kim, Se-Ho Lee

ECCV 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 0 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
use decoupled alternating color/geometry optimization instead of joint-step (ablation)geometry-aware 3DGS style transfer · 72 scene-style combinationsSIFID: 1.4220 -> 1.1736Improved
add geometry updates to color-only optimization (ablation)geometry-aware 3DGS style transfer · 72 scene-style combinationsSIFID: 1.5392 -> 1.1736Improved
add color updates to geometry-only optimization (ablation)geometry-aware 3DGS style transfer · 72 scene-style combinationsSIFID: 2.5496 -> 1.1736Improved
decoupled instead of joint-step (ablation)geometry-aware 3DGS style transfer · long-range consistencyLPIPS: 0.122 -> 0.114Improved
decoupled instead of only geometry (ablation)geometry-aware 3DGS style transfer · long-range consistencyLPIPS: 0.113 -> 0.114No clear effect
increase geometry update steps from 0 to 90 of 100 per cycle (ablation)geometry-aware 3DGS style transfer · 72 scene-style combinationsSIFID: 1.5244 -> 1.1736Improved
use all 100 geometry updates instead of 90 (ablation)geometry-aware 3DGS style transfer · 72 scene-style combinationsSIFID: 1.1736 -> 1.1885Hurt
add GCFM loss (lambda_GC 0.0 to 2.0) (ablation)geometry-aware 3DGS style transfer · 72 scene-style combinationsSIFID: 1.5718 -> 1.1736Improved
vary lambda_GC from 1.0 to 5.0 (ablation)geometry-aware 3DGS style transfer · 72 scene-style combinationsSIFID: 1.1683 -> 1.1841No clear effect
add contrastive objective to GCFM (ablation)geometry-aware 3DGS style transfer · depth map structurequalitativeImproved
use multi-modal color/depth/edge features instead of single modality (ablation)geometry-aware 3DGS style transfer · depth map structurequalitativeImproved
compare against StylizedGS on consistencyOurs vs StylizedGS · long-range consistencyRMSE: 0.062 -> 0.084Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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