AI Paper Atlas

Research map / 3D vision / 3D generation

CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization

Weilin Chen, Jiahao Rao, Wenhao Wang, Xinyang Li, Xuan Cheng, Liujuan Cao

CVPR 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 pixel-level (super-resolution) distillation (ablation)CustomTex · 3D-FRONT (10 scenes), image-to-textureQ-Align IQA: 3.330 -> 4.469Improved
add pixel-level distillation (ablation)CustomTex · 3D-FRONT (10 scenes), image-to-textureCLIP-FID: 118.247 -> 106.229Improved
apply instance masks at feature level of cross-attention instead of noise level (ablation)CustomTex · 3D-FRONT (10 scenes), image-to-textureQ-Align IQA: 3.689 -> 4.469Improved
use multiple separate reference images instead of one stitched image (ablation)CustomTex · 3D-FRONT (10 scenes), image-to-textureCLIP-I: 0.757 -> 0.797Improved
use multiple separate reference images instead of one stitched image (ablation)CustomTex · 3D-FRONT (10 scenes), image-to-textureQ-Align IAA: 3.519 -> 3.629Improved
CustomTex vs SceneTex-IPA (image prompts)indoor scene texturing · 3D-FRONT (10 scenes), image-to-textureCLIP-I: 0.741 -> 0.797Improved
CustomTex (GPT-4v reference images) vs SceneTex with text promptsindoor scene texturing · 3D-FRONT (10 scenes), text-to-textureCLIP-T: 0.639 -> 0.766Improved

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