AI Paper Atlas

Research map / 3D vision / 3D generation

UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes

Yixun Liang, Kunming Luo, Xiao Chen, Rui Chen, Hongyu Yan, Weiyu Li, Jiarui Liu, Fei-Peng Tian, Ping Tan

CVPR 2026 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 27 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 Texture Function supervision (volumetric) instead of surface-only supervision (ablation)Large Texturing Model · full-model texturingPSNR: 25.81 -> 27.01Improved
add Texture Function supervision (ablation)Large Texturing Model · full-model texturingPSNR_uv: 20.31 -> 20.99Improved
drop 50% of tokens during MV generation training (drop training) (ablation)Flux MV generation · artist-created meshtraining memory (GB): 69.2GB -> 53.6GBImproved
add drop training (ablation)Flux MV generation · artist-created meshtraining step time (s/it): 38.76s/it -> 21.50s/itImproved
add drop training (ablation)Flux MV generation · artist-created meshFID_CLIP: 17.49 -> 16.03No clear effect
add drop training (ablation)Flux MV generation · artist-created meshLPIPS: 0.087 -> 0.090No clear effect
use 3D LTM refinement instead of UV-based refinementUniTEX second stage · artist-created meshPSNR_uv: 20.47 -> 23.01Improved
use UniTEX instead of Hunyuan3D-Painttexturing pipeline · artist-created meshFID_CLIP: 20.38 -> 16.03Improved
use UniTEX instead of Hunyuan3D-Painttexturing pipeline · artist-created meshLPIPS: 0.091 -> 0.090No clear effect
use UniTEX instead of Hunyuan3D-Painttexturing pipeline · generative meshuser preference (%): 21.36% -> 65.91%Improved
use native 3D single-stage TexGaussians instead of 2D-prior two-stagetexturing pipeline · generative meshCLIPscore: 0.807 -> 0.681Hurt

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