AI Paper Atlas

Research map / 3D vision / 3D generation

RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis

Yifei Feng, Mingxin Yang, Shuhui Yang, Sheng Zhang, Jiaao Yu, Zibo Zhao, Yuhong Liu, Jie Jiang, Chunchao Guo

ICCV 2025 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 14 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 3D-aware RoPE in multi-view attention (ablation)RomanTex · multi-view consistency (qualitative)visual consistencyImproved
add decoupled reference branch (MVA dropout) (ablation)RomanTex · back-view texture (qualitative)visual qualityImproved
add geometry-related CFG at inference (ablation)RomanTex · geometry alignment (qualitative)visual alignmentImproved
RomanTex vs HY3D-2.0 multi-view baselineHY3D-2.0 · Text-to-textureCLIP-FID: 26.44 -> 24.78Improved
RomanTex vs HY3D-2.0 multi-view baselineHY3D-2.0 · Text-to-textureCMMD: 2.318 -> 2.191Improved
RomanTex vs HY3D-2.0 multi-view baselineHY3D-2.0 · Text-to-textureLPIPS: 0.136 -> 0.121Improved
RomanTex vs Text2tex on text alignmentText2tex · Text-to-textureCLIP-T: 0.318 vs 0.308No clear effect
RomanTex vs HY3D-2.0HY3D-2.0 · Image-to-textureCLIP-FID: 26.439 -> 24.78Improved
RomanTex vs Paint3D-IPA on image fidelityPaint3D-IPA · Image-to-textureCLIP-I: 0.998 vs 0.891Hurt
RomanTex vs HY3D-2.0 in user studyHY3D-2.0 · Image-to-texture user studyoverall quality Q (%): 20.7 -> 63.9Improved

Earlier methods this paper compares with

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