UltraTex: Unleashing 2K Multi-View Diffusion for 3D Texturing

Hugging Face Daily Papers Papers
3d-texturing multi-view-diffusion high-resolution efficiency diffusion-models computer-vision

Summary

UltraTex is an efficient framework for high-resolution multi-view diffusion-based 3D texturing, introducing techniques to reduce redundancy and achieve significant speedups in training and inference.

High-quality texture generation is essential for creating realistic and production-ready 3D assets. Recent multi-view diffusion methods have shown promising results for image-guided 3D texturing, but they are typically constrained to low operating resolutions such as 512 or 768, making it difficult to preserve high-frequency details from high-resolution reference images. Scaling this paradigm to 2048 resolution is computationally prohibitive, as the unified multi-view sequence exceeds 212K tokens and incurs excessive memory and latency. In this paper, we present UltraTex, an efficient end-to-end framework for high-resolution multi-view diffusion-based 3D texturing. Our key observation is that object-centric multi-view renderings contain two major sources of redundancy: background-induced sequence redundancy and sparse token interactions within the foreground. To address them, we introduce Background Token Dropping, which removes background tokens before the DiT backbone, and Block-Sparse Attention, which reduces attention computation over the retained foreground sequence. To enable efficient foreground-only inference while avoiding reconstruction artifacts, we further design Foreground-Aware VAE Decoding to ensure the quality of the final high-resolution views. To satisfy the demanding data requirements of 2K-resolution multi-view diffusion training, we construct G-buffer TexVerse, a large-scale, ultra-high-resolution multi-view rendering dataset covering over 268,000 3D assets. Extensive experiments show that UltraTex generates visually faithful textures with rich fine-grained details, while substantially improving efficiency, achieving 20.6times--91.1times training speedup and 22.3times--74.6times end-to-end inference speedup over the baseline on common samples in our dataset. Code and data is at https://yiboz2001.github.io/UltraTex.
Original Article
View Cached Full Text

Cached at: 09/22/26, 03:27 PM

Paper page - UltraTex: Unleashing 2K Multi-View Diffusion for 3D Texturing

Source: https://huggingface.co/papers/2609.23169

Abstract

High-qualitytexturegenerationisessentialforcreatingrealisticandproduction-ready3Dassets.Recentmulti-viewdiffusionmethodshaveshownpromisingresultsforimage-guided3Dtexturing,buttheyaretypicallyconstrainedtolowoperatingresolutionssuchas512or768,makingitdifficulttopreservehigh-frequencydetailsfromhigh-resolutionreferenceimages.Scalingthisparadigmto2048resolutioniscomputationallyprohibitive,astheunifiedmulti-viewsequenceexceeds212Ktokensandincursexcessivememoryandlatency.Inthispaper,wepresentUltraTex,anefficientend-to-endframeworkforhigh-resolutionmulti-viewdiffusion-based3Dtexturing.Ourkeyobservationisthatobject-centricmulti-viewrenderingscontaintwomajorsourcesofredundancy:background-inducedsequenceredundancyandsparsetokeninteractionswithintheforeground.Toaddressthem,weintroduceBackgroundTokenDropping,whichremovesbackgroundtokensbeforetheDiTbackbone,andBlock-SparseAttention,whichreducesattentioncomputationovertheretainedforegroundsequence.Toenableefficientforeground-onlyinferencewhileavoidingreconstructionartifacts,wefurtherdesignForeground-AwareVAEDecodingtoensurethequalityofthefinalhigh-resolutionviews.Tosatisfythedemandingdatarequirementsof2K-resolutionmulti-viewdiffusiontraining,weconstructG-bufferTexVerse,alarge-scale,ultra-high-resolutionmulti-viewrenderingdatasetcoveringover268,0003Dassets.ExtensiveexperimentsshowthatUltraTexgeneratesvisuallyfaithfultextureswithrichfine-graineddetails,whilesubstantiallyimprovingefficiency,achieving20.6times--91.1timestrainingspeedupand22.3times--74.6timesend-to-endinferencespeedupoverthebaselineoncommonsamplesinourdataset.Codeanddataisathttps://yiboz2001.github.io/UltraTex.

View arXiv pageView PDFProject pageGitHub2Add to collection

Get this paper in your agent:

hf papers read 2609\.23169

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.23169 in a model README.md to link it from this page.

Datasets citing this paper1

#### YiboZhang2001/G-buffer-TexVerse Updatedabout 7 hours ago • 21

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.23169 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing

arXiv cs.CL

UltraX proposes a function-calling refinement framework for large-scale pre-training data that introduces insertion alongside deletion and modification, enabling fine-grained instance-level editing. It builds a reliable program-supervision generation pipeline and demonstrates improved data efficiency and model performance when pretraining 1B models from scratch.