RefAny3D: 3D Asset-Referenced Diffusion Models for Image Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918313855025152 |
|---|---|
| author | Huang, Hanzhuo Bao, Qingyang Gu, Zekai Du, Zhongshuo Lin, Cheng Liu, Yuan Yang, Sibei |
| author_facet | Huang, Hanzhuo Bao, Qingyang Gu, Zekai Du, Zhongshuo Lin, Cheng Liu, Yuan Yang, Sibei |
| contents | In this paper, we propose a 3D asset-referenced diffusion model for image generation, exploring how to integrate 3D assets into image diffusion models. Existing reference-based image generation methods leverage large-scale pretrained diffusion models and demonstrate strong capability in generating diverse images conditioned on a single reference image. However, these methods are limited to single-image references and cannot leverage 3D assets, constraining their practical versatility. To address this gap, we present a cross-domain diffusion model with dual-branch perception that leverages multi-view RGB images and point maps of 3D assets to jointly model their colors and canonical-space coordinates, achieving precise consistency between generated images and the 3D references. Our spatially aligned dual-branch generation architecture and domain-decoupled generation mechanism ensure the simultaneous generation of two spatially aligned but content-disentangled outputs, RGB images and point maps, linking 2D image attributes with 3D asset attributes. Experiments show that our approach effectively uses 3D assets as references to produce images consistent with the given assets, opening new possibilities for combining diffusion models with 3D content creation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22094 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RefAny3D: 3D Asset-Referenced Diffusion Models for Image Generation Huang, Hanzhuo Bao, Qingyang Gu, Zekai Du, Zhongshuo Lin, Cheng Liu, Yuan Yang, Sibei Computer Vision and Pattern Recognition In this paper, we propose a 3D asset-referenced diffusion model for image generation, exploring how to integrate 3D assets into image diffusion models. Existing reference-based image generation methods leverage large-scale pretrained diffusion models and demonstrate strong capability in generating diverse images conditioned on a single reference image. However, these methods are limited to single-image references and cannot leverage 3D assets, constraining their practical versatility. To address this gap, we present a cross-domain diffusion model with dual-branch perception that leverages multi-view RGB images and point maps of 3D assets to jointly model their colors and canonical-space coordinates, achieving precise consistency between generated images and the 3D references. Our spatially aligned dual-branch generation architecture and domain-decoupled generation mechanism ensure the simultaneous generation of two spatially aligned but content-disentangled outputs, RGB images and point maps, linking 2D image attributes with 3D asset attributes. Experiments show that our approach effectively uses 3D assets as references to produce images consistent with the given assets, opening new possibilities for combining diffusion models with 3D content creation. |
| title | RefAny3D: 3D Asset-Referenced Diffusion Models for Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.22094 |