Dual Diffusion Models for Multi-modal Guided 3D Avatar Generation

• URL: http://arxiv.org/abs/2603.04307v1
• Date: Wed, 04 Mar 2026 17:24:28 GMT
• Title: Dual Diffusion Models for Multi-modal Guided 3D Avatar Generation
• Authors: Hong Li, Yutang Feng, Minqi Meng, Yichen Yang, Xuhui Liu, Baochang Zhang,
• Abstract summary: We present PromptAvatar, a framework for generating high-fidelity 3D avatars from text or image prompts.<n>It learns the direct mapping from multi-modal prompts to 3D representations, successfully generating high-fidelity, shading-free 3D avatars in under 10 seconds.<n>Our method significantly outperforms existing state-of-the-art approaches in generation quality, fine-grained detail alignment, and computational efficiency.
• Score: 19.94446175293186
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Generating high-fidelity 3D avatars from text or image prompts is highly sought after in virtual reality and human-computer interaction. However, existing text-driven methods often rely on iterative Score Distillation Sampling (SDS) or CLIP optimization, which struggle with fine-grained semantic control and suffer from excessively slow inference. Meanwhile, image-driven approaches are severely bottlenecked by the scarcity and high acquisition cost of high-quality 3D facial scans, limiting model generalization. To address these challenges, we first construct a novel, large-scale dataset comprising over 100,000 pairs across four modalities: fine-grained textual descriptions, in-the-wild face images, high-quality light-normalized texture UV maps, and 3D geometric shapes. Leveraging this comprehensive dataset, we propose PromptAvatar, a framework featuring dual diffusion models. Specifically, it integrates a Texture Diffusion Model (TDM) that supports flexible multi-condition guidance from text and/or image prompts, alongside a Geometry Diffusion Model (GDM) guided by text prompts. By learning the direct mapping from multi-modal prompts to 3D representations, PromptAvatar eliminates the need for time-consuming iterative optimization, successfully generating high-fidelity, shading-free 3D avatars in under 10 seconds. Extensive quantitative and qualitative experiments demonstrate that our method significantly outperforms existing state-of-the-art approaches in generation quality, fine-grained detail alignment, and computational efficiency.

Related papers

• Wonder3D++: Cross-domain Diffusion for High-fidelity 3D Generation from a Single Image [68.55613894952177]
  We introduce textbfWonder3D++, a novel method for efficiently generating high-fidelity textured meshes from single-view images.<n>We propose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images.<n> Lastly, we introduce a cascaded 3D mesh extraction algorithm that drives high-quality surfaces from the multi-view 2D representations in only about $3$ minute in a coarse-to-fine manner.
  arXiv  Detail & Related papers  (2025-11-03T17:24:18Z)
• Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data [80.92268916571712]
  A critical bottleneck is the scarcity of high-quality 3D objects with detailed captions. We propose Bootstrap3D, a novel framework that automatically generates an arbitrary quantity of multi-view images. We have generated 1 million high-quality synthetic multi-view images with dense descriptive captions.
  arXiv  Detail & Related papers  (2024-05-31T17:59:56Z)
• Grounded Compositional and Diverse Text-to-3D with Pretrained Multi-View Diffusion Model [65.58911408026748]
  We propose Grounded-Dreamer to generate 3D assets that can accurately follow complex, compositional text prompts. We first advocate leveraging text-guided 4-view images as the bottleneck in the text-to-3D pipeline. We then introduce an attention refocusing mechanism to encourage text-aligned 4-view image generation.
  arXiv  Detail & Related papers  (2024-04-28T04:05:10Z)
• IT3D: Improved Text-to-3D Generation with Explicit View Synthesis [71.68595192524843]
  This study presents a novel strategy that leverages explicitly synthesized multi-view images to address these issues. Our approach involves the utilization of image-to-image pipelines, empowered by LDMs, to generate posed high-quality images. For the incorporated discriminator, the synthesized multi-view images are considered real data, while the renderings of the optimized 3D models function as fake data.
  arXiv  Detail & Related papers  (2023-08-22T14:39:17Z)
• Guide3D: Create 3D Avatars from Text and Image Guidance [55.71306021041785]
  Guide3D is a text-and-image-guided generative model for 3D avatar generation based on diffusion models. Our framework produces topologically and structurally correct geometry and high-resolution textures.
  arXiv  Detail & Related papers  (2023-08-18T17:55:47Z)
• StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation [103.88928334431786]
  We present a novel method for generating high-quality, stylized 3D avatars. We use pre-trained image-text diffusion models for data generation and a Generative Adversarial Network (GAN)-based 3D generation network for training. Our approach demonstrates superior performance over current state-of-the-art methods in terms of visual quality and diversity of the produced avatars.
  arXiv  Detail & Related papers  (2023-05-30T13:09:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.