# Does Native 3D Texture Generation Necessarily Require 3D Assets for Training?

arXiv: https://arxiv.org/abs/2609.34621 · HTML: https://mlsanity.com/paper/2609.34621/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 27 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset](https://mlsanity.com/paper/2505.09568/) (2025)
- [TEXTure: Text-Guided Texturing of 3D Shapes](https://mlsanity.com/paper/2302.01721/) (2023)
- [Text2Tex: Text-driven Texture Synthesis via Diffusion Models](https://mlsanity.com/paper/2303.11396/) (2023)
- [Native and Compact Structured Latents for 3D Generation](https://mlsanity.com/paper/2512.14692/) (2025)
- [Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material](https://mlsanity.com/paper/2506.15442/) (2025)
- [Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models](https://mlsanity.com/paper/2312.13913/) (2023)
- [Text-Guided Texturing by Synchronized Multi-View Diffusion](https://mlsanity.com/paper/2311.12891/) (2023)
- [VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models](https://mlsanity.com/paper/2403.12034/) (2024)
- [TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion](https://mlsanity.com/paper/2401.09416/) (2024)
- [TEXGen: a Generative Diffusion Model for Mesh Textures](https://mlsanity.com/paper/2411.14740/) (2024)
- [LRM-Zero: Training Large Reconstruction Models with Synthesized Data](https://mlsanity.com/paper/2406.09371/) (2024)
- [MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D](https://mlsanity.com/paper/2411.02336/) (2024)
- [TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting](https://mlsanity.com/paper/2411.19654/) (2024)
- [MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion](https://mlsanity.com/paper/2503.10289/) (2025)
- [TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and Resampling](https://mlsanity.com/paper/2408.01291/) (2024)
- [UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes](https://mlsanity.com/paper/2505.23253/) (2025)
- [MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data](https://mlsanity.com/paper/2412.14166/) (2024)
- [NaTex: Seamless Texture Generation as Latent Color Diffusion](https://mlsanity.com/paper/2511.16317/) (2025)
- [LaFiTe: A Generative Latent Field for 3D Native Texturing](https://mlsanity.com/paper/2512.04786/) (2025)
- [Hitem3D 2.0: Multi-View Guided Native 3D Texture Generation](https://mlsanity.com/paper/2604.09231/) (2026)

## Built on by (most cited first, 2 of 2)

- [MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers](https://mlsanity.com/paper/2610.06801/) (2026)
- [Position Forcing: Self-Conditioning 3D Generation](https://mlsanity.com/paper/2610.10342/) (2026)

## Abstract (arXiv)

Native 3D texture generation synthesizes colors directly in 3D space for a given geometry, conditioned on multi-view reference images. It is generally believed that training such models requires large-scale, high-quality real 3D asset data, whose acquisition remains a long-standing and challenging problem. In this work, we propose Tex-Zero, demonstrating that a high-fidelity native 3D texture generation framework can be trained without 3D assets. Our key observation is that only high-quality and fine-grained color information is essential for 3D texture training, while the required geometric information is less critical and can be manually constructed rather than obtained from real 3D assets. This finding makes it possible to transform abundant, high-quality 2D images into effective training samples for 3D texture generation. Specifically, we convert high-quality 2D images into 3D training samples by representing each image as a plane in 3D space and applying patch-wise random rotations and aggregation to construct complex geometric structures. Using these constructed image data, we train the Tex-Zero VAE, which can reconstruct real 3D assets with high quality despite never observing them during training. Building upon the Tex-Zero VAE, we train the Tex-Zero DiT also exclusively on the constructed image data, where the conditioning 2D multi-view images are transformed into planes in 3D space and also encoded by the Tex-Zero VAE, thereby reducing the representation gap and improving generation quality. Extensive experiments show that Tex-Zero generates high-fidelity 3D textures with fine-grained details solely using images as training data, offering a promising perspective on the data paradigm for scaling 3D texture generation.