MD-ProjTex: Texturing 3D Shapes with Multi-Diffusion Projection

2025/04/03 by Ahmet Burak Yildirim, Yildirim, Ahmet Burak, Mustafa Utku Aydogdu +6 · 1 voice · 1 citation
Computer Science · Engineering · #3D Shape Modeling and Analysis #Additive Manufacturing and 3D Printing Technologies #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV

paper · pdf · doi:10.48550/arxiv.2504.02762

openalex publication_date 2025/04/03 · arxiv published 2025/04/03 · arxiv updated 2025/04/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We introduce MD-ProjTex, a method for fast and consistent text-guided texture generation for 3D shapes using pretrained text-to-image diffusion models. At the core of our approach is a multi-view consistency mechanism in UV space, which ensures coherent textures across different viewpoints. Specifically, MD-ProjTex fuses noise predictions from multiple views at each diffusion step and jointly updates the per-view denoising directions to maintain 3D consistency. In contrast to existing state-of-the-art methods that rely on optimization or sequential view synthesis, MD-ProjTex is computationally more efficient and achieves better quantitative and qualitative results.

Citations

• TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and Resampling
• Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objects
• DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models
• TexPainter: Generative Mesh Texturing with Multi-view Consistency
• IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation
• SPAD : Spatially Aware Multiview Diffusers
• Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models
• Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning
• Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering
• EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion
• Free3D: Consistent Novel View Synthesis without 3D Representation
• Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model
• Texture Generation on 3D Meshes with Point-UV Diffusion
• IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
• Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
• Progressive Learning of 3D Reconstruction Network from 2D GAN Data
• Text2Tex: Text-driven Texture Synthesis via Diffusion Models
• Refining 3D Human Texture Estimation from a Single Image
• MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation
• Adding Conditional Control to Text-to-Image Diffusion Models
• Adding Conditional Control to Text-to-Image Diffusion Models
• UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models
• TEXTure: Text-Guided Texturing of 3D Shapes
• Objaverse: A Universe of Annotated 3D Objects
• Magic3D: High-Resolution Text-to-3D Content Creation
• Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures
• eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
• DreamFusion: Text-to-3D using 2D Diffusion
• GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images
• Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• CLIP-Mesh: Generating textured meshes from text using pretrained image-text models
• Fine Detailed Texture Learning for 3D Meshes with Generative Models
• StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation
• High-Resolution Image Synthesis with Latent Diffusion Models
• High-Resolution Image Synthesis with Latent Diffusion Models
• GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
• Efficient Geometry-aware 3D Generative Adversarial Networks
• StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis
• pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
• GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields
• Denoising Diffusion Probabilistic Models
• AvatarMe: Realistically Renderable 3D Facial Reconstruction "in-the-wild"
• Analyzing and Improving the Image Quality of StyleGAN
• Accelerating 3D Deep Learning with PyTorch3D
• Predicting 3D Human Dynamics from Video
• HoloGAN: Unsupervised learning of 3D representations from natural images
• GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop

Cited by

• 3D Stylization via Large Reconstruction Model

Discussions

• 📄 Paper: arxiv.org/abs/2504.02762 🌐 Project page: mdprojtex.abyildirim.com [bsky, 0 points, 0 comments]

Related

• TexPainter: Generative Mesh Texturing with Multi-view Consistency
• Consistent Mesh Diffusion
• Text2Tex: Text-driven Texture Synthesis via Diffusion Models
• GenesisTex2: Stable, Consistent and High-Quality Text-to-Texture Generation
• Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion