MV2UV: Generating High-quality UV Texture Maps with Multiview Prompts

Zheng Zhang; Qinchuan Zhang; Yuteng Ye; Zhi Chen; Penglei Ji; Mengfei Li; Wenxiao Zhang; Yuan Liu

cs.CVMar 16, 2026

MV2UV: Generating High-quality UV Texture Maps with Multiview Prompts

Authors: Zheng Zhang, Qinchuan Zhang, Yuteng Ye, Zhi Chen, Penglei Ji, Mengfei Li, Wenxiao Zhang, Yuan Liu

Organizations: Hisilicon Linx Lab, Huawei · Hong Kong University of Science and Technology

Abstract

Generating high-quality textures for 3D assets is a challenging task. Existing multiview texture generation methods suffer from the multiview inconsistency and missing textures on unseen parts, while UV inpainting texture methods do not generalize well due to insufficient UV data and cannot well utilize 2D image diffusion priors. In this paper, we propose a new method called MV2UV that combines 2D generative priors from multiview generation and the inpainting ability of UV refinement to get high-quality texture maps. Our key idea is to adopt a UV space generative model that simultaneously inpaints unseen parts of multiview images while resolving the inconsistency of multiview images. Experiments show that our method enables a better texture generation quality than existing methods, especially in unseen occluded and multiview-inconsistent parts.

Figures & tables

Figure 1: The Overview of our MV2UV framework. We first generate multiview images (MVs) using multiview diffusion (MVD). Then, we treat the generated MVs as semantic prompts to guide texture generation on the UV map. The generation process is based on a diffusion U-Net, which primarily consists of Self Attention, UV Self Attention, and Reference Attention modules.

Figure 2: We apply the 3D coordinates as the positional encoding within MV-UV cross attention, enabling the UV map to attend to geometrically corresponding regions on multiview images for improved inpainting and inconsistency resolution.

Figure 3: The geometric position encoding. We first render the object mesh to obtain normal and position maps, which are processed in two separate branches: one in UV space and the other in view space. In each branch, the corresponding geometric maps are transformed into positional embeddings and further encoded by a learnable position encoder to produce geometric features.

Figure 4: The UV Islands. UV self attention enables the model to establish correlations between UV regions (e.g., $P_{A}$ and $P_{B}$ ) that are adjacent in 3D space, even when they are disconnected in the UV layout.

Figure 5: Comparisons with texture generation methods from a single image input. Our method enables automatic completion of textures in occluded UV regions while avoiding inconsistencies induced by direct projection.

Figure 6: Qualitative comparison on occluded regions. The occlusion mask (left), MV-Adapter results (middle), and our results (right) demonstrate our method’s capability in resolving view inconsistencies and producing more semantically coherent results.

Method	GSO Dataset		DTC Dataset
Method	FID ( $\downarrow$ )	KID ( $\downarrow$ )	FID ( $\downarrow$ )	KID ( $\downarrow$ )
TEXGen	75.2	283.3	41.1	118.6
Hunyuan3D 2.1	30.8	72.5	41.4	49.9
UniTEX	39.2	101.5	39.7	43.3
MV-Adapter	24.7	47.5	28.4	41.8
Ours	24.4	43.6	26.4	28.7

Table 1: Performance comparison of material generation methods. Our approach achieves the best FID and KID scores on both datasets, demonstrating superior performance.

Method	FID ( $\downarrow$ )	KID ( $\downarrow$ )
MV-Adapter	123.6	157.9
Ours	67.5	47.6

Table 2: Quantitative evaluation on occluded regions. FID and KID are computed between rendered images and the ground truth forced on occluded part. Our method achieves superior performance over the MV-Adapter baseline.

Figure 7: The generated results with rendered views.

Dataset	Metrics
Dataset	PSNR $\uparrow$	SSIM $\uparrow$	FID $\downarrow$	KID $\downarrow$
GSO	25.7	0.855	3.32	8.49
$GSO_{c}$	25.5	0.852	4.03	10.6
DTC	28.8	0.886	5.44	14.9
$DTC_{c}$	28.6	0.885	5.90	16.4

Table 3: Ablation study on View-inconsistency Resolution.

Configuration	GSO Dataset		DTC Dataset
	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$
w/o Pos Enc	13.6	0.688	13.9	0.689
w/o Ref Attn	18.9	0.805	22.6	0.861
w/o UV Attn	21.5	0.814	23.9	0.863
Full Model	25.7	0.855	28.8	0.886

Table 4: Ablation study on GSO and DTC datasets. Configurations: without geometric position encoding (w/o Pos Enc), reference attention (w/o Ref Attn), UV self attention (w/o UV Attn).

Figure 9: Detail of Learnable Position Encoder.

Figure 10: MV2UV can generate diverse, high-quality textures from different prompts, enabling flexible and controllable texture synthesis.

3D Texture Generation

See all 19 papers

UltraTex: Unleashing 2K Multi-View Diffusion for 3D Texturing
Sep 19, 2026Yibo Zhang, Ze Yuan, Nan Cao +4Multi-View Image Synthesis 3D Texture Generation
Jilin University, Changchun, China · Shanghai Innovation Institute, Shanghai, China · The University of Hong Kong, Hong Kong, China +3
DirectUV: Image-Conditioned UV Texture Generation with Surface-Aware Positional Encoding
Sep 28, 2026Jiantao Lin, Yingjie Xu, Mingzhi Sheng +3Latent Diffusion Models Positional Encoding
The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology
FlexPainter: Flexible and Multi-View Consistent Texture Generation
Jun 3, 2025Dongyu Yan, Leyi Wu, Jiantao Lin +7Multi-View Image Synthesis 3D Texture Generation
HKUST(GZ) · Quwan · HKUST

Sep 19, 2026J/K move · Enter open · S save

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

Yibo Zhang, Ze Yuan, Nan Cao, Li Zhang+3

Jilin University, Changchun, China · Shanghai Innovation Institute, Shanghai, China · The University of Hong Kong, Hong Kong, China+3

Multi-View Image Synthesis 3D Texture Generation Texture Synthesis Image Generation Diffusion Model Acceleration Diffusion Transformer

Open paper AskPDF arXiv

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

20.6\times

91.1\times

training speedup and

22.3\times

74.6\times

end-to-end inference speedup over the baseline on common samples in our dataset. Code and data is at https://yiboz2001.github.io/UltraTex.

Abstract

3D Texture Generation

Explore similar work

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

DirectUV: Image-Conditioned UV Texture Generation with Surface-Aware Positional Encoding

FlexPainter: Flexible and Multi-View Consistent Texture Generation