AI Paper Atlas

Research map / 3D vision / 3D generation

DiffStyle3D: Consistent 3D Gaussian Stylization via Attention Optimization

Yitong Yang, Yinglin Wang, Xuexin Liu, Jing Wang, Hao Dou, Changshuo Wang, Shuting He

ICML 2026 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 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
add Geometry-Guided Attention across views (ablation)DiffStyle3D · scene-level 3DGS stylizationCLIP-CONS: 0.121 -> 0.128Improved
add Geometry-Guided Attention across views (ablation)DiffStyle3D · scene-level 3DGS stylizationlong-range LPIPS: 0.151 -> 0.141Improved
add geometry-aware mask MG (ablation)DiffStyle3D · scene-level 3DGS stylizationCLIP-CONS: 0.124 -> 0.128No clear effect
add centering and normalization to attention losses (ablation)Attention-Aware Loss · qualitative style transfer convergencestyle transfer speedImproved
inject style K and V into rendered Q instead of using style image attention output directly (ablation)style loss · qualitativecontent leakageImproved
use fixed timestep t=1 instead of large, random or decreasing timesteps (ablation)DiffStyle3D · qualitativestylization detailImproved
optimize in diffusion latent space with attention loss instead of denoising directions3DGS stylization · scene-level 3DGSFID: 228.6 -> 204.8Improved
use diffusion attention features rather than CLIP features3DGS stylization · scene-level 3DGSCLIP-S: 0.79 -> 0.65Hurt
use diffusion attention instead of CLIP features3DGS stylization · object-level 3DGSCLIP-CONS: 0.504 -> 0.412Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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