AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Stylos: Multi-View 3D Stylization with Single-Forward Gaussian Splatting

Hanzhou Liu, Jia Huang, Mi Lu, Srikanth Saripalli, Peng Jiang

ICLR 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views

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 Global CrossBlock instead of Global+Frame hybrid (ablation)Stylos · CO3D pizzaPSNR: 19.78 -> 20.57Improved
use Frame CrossBlock only instead of hybrid (ablation)Stylos · CO3D pizzaPSNR: 19.78 -> 19.72No clear effect
use Global CrossBlock instead of Frame only (ablation)Stylos · CO3D skateboardPSNR: 20.93 -> 21.68Improved
use scene-level style loss instead of image-level (ablation)Stylos · CO3D held-out scenesArtScore: 4.78 -> 9.12Improved
use voxel-level 3D style loss instead of scene-level (ablation)Stylos · CO3D held-out scenesshort-range RMSE: 0.036 -> 0.034Improved
use voxel-level 3D style loss instead of image-level (ablation)Stylos · CO3D held-out sceneslong-range LPIPS: 0.157 -> 0.153Improved
use voxel-level 3D style loss instead of scene-level (ablation)Stylos · CO3D held-out scenesArtScore: 9.12 -> 9.15No clear effect
use voxel-level 3D style loss instead of image-level (ablation)Stylos · CO3D held-out sceneslong-range RMSE: 0.142 -> 0.142No clear effect
increase views per batch beyond 32 (up to 64) (ablation)Stylos · Tanks & Temples Lighthousevisual qualityHurt
use a single view per batch (ablation)Stylos · Tanks & Temples Lighthousevisual qualityHurt
use single-forward Stylos instead of per-scene methodsStylos · Tanks & Templesstylization time: 0.05 s vs 14.7 m (G-Style)Improved

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