# 3D Stylization via Large Reconstruction Model

arXiv: https://arxiv.org/abs/2504.21836 · HTML: https://mlsanity.com/paper/2504.21836/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 55 references that are in the map.
- First posted on arXiv 30 Apr 2025.

## Builds on (most cited first, 30 of 40)

- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization](https://mlsanity.com/paper/2306.16928/) (2023)
- [Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model](https://mlsanity.com/paper/2310.15110/) (2023)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models](https://mlsanity.com/paper/2404.07191/) (2024)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation](https://mlsanity.com/paper/2301.07525/) (2023)
- [Learning Category-Specific Mesh Reconstruction from Image Collections](https://mlsanity.com/paper/1803.07549/) (2018)
- [GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation](https://mlsanity.com/paper/2403.14621/) (2024)
- [Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer](https://mlsanity.com/paper/1908.01210/) (2019)
- [InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation](https://mlsanity.com/paper/2404.02733/) (2024)
- [MeshLRM: Large Reconstruction Model for High-Quality Meshes](https://mlsanity.com/paper/2404.12385/) (2024)
- [Cross-Image Attention for Zero-Shot Appearance Transfer](https://mlsanity.com/paper/2311.03335/) (2023)
- [Self-supervised Single-view 3D Reconstruction via Semantic Consistency](https://mlsanity.com/paper/2003.06473/) (2020)
- [RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models](https://mlsanity.com/paper/2312.04524/) (2023)
- [Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning](https://mlsanity.com/paper/2205.09542/) (2022)
- [Shape and Viewpoint without Keypoints](https://mlsanity.com/paper/2007.10982/) (2020)
- [V3D: Video Diffusion Models are Effective 3D Generators](https://mlsanity.com/paper/2403.06738/) (2024)
- [StyleGaussian: Instant 3D Style Transfer with Gaussian Splatting](https://mlsanity.com/paper/2403.07807/) (2024)
- [Leveraging 2D Data to Learn Textured 3D Mesh Generation](https://mlsanity.com/paper/2004.04180/) (2020)
- [Visual Style Prompting with Swapping Self-Attention](https://mlsanity.com/paper/2402.12974/) (2024)
- [A Closed-form Solution to Universal Style Transfer](https://mlsanity.com/paper/1906.00668/) (2019)
- [AID: Attention Interpolation of Text-to-Image Diffusion](https://mlsanity.com/paper/2403.17924/) (2024)

## Built on by (most cited first, 8 of 8)

- [Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles](https://mlsanity.com/paper/2505.21060/) (2025)
- [VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image](https://mlsanity.com/paper/2602.04349/) (2026)
- [Jigsaw3D: Disentangled 3D Style Transfer via Patch Shuffling and Masking](https://mlsanity.com/paper/2510.10497/) (2025)
- [DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglement](https://mlsanity.com/paper/2607.24721/) (2026)
- [StyleFusion360: View-Consistent Head Stylization via Adaptive Style Modulation](https://mlsanity.com/paper/2511.22411/) (2025)
- [SIC3D: Style Image Conditioned Text-to-3D Gaussian Splatting Generation](https://mlsanity.com/paper/2604.08760/) (2026)
- [Owner3D: Ownership-Guided Style Writing for Training-Free Localized 3D Stylization](https://mlsanity.com/paper/2608.14078/) (2026)
- [OrnaStyler: Ornament-Aware Latent Editing for Content-Preserving 3D Stylization](https://mlsanity.com/paper/2608.29905/) (2026)

## Abstract (arXiv)

With the growing success of text or image guided 3D generators, users demand more control over the generation process, appearance stylization being one of them. Given a reference image, this requires adapting the appearance of a generated 3D asset to reflect the visual style of the reference while maintaining visual consistency from multiple viewpoints. To tackle this problem, we draw inspiration from the success of 2D stylization methods that leverage the attention mechanisms in large image generation models to capture and transfer visual style. In particular, we probe if large reconstruction models, commonly used in the context of 3D generation, has a similar capability. We discover that the certain attention blocks in these models capture the appearance specific features. By injecting features from a visual style image to such blocks, we develop a simple yet effective 3D appearance stylization method. Our method does not require training or test time optimization. Through both quantitative and qualitative evaluations, we demonstrate that our approach achieves superior results in terms of 3D appearance stylization, significantly improving efficiency while maintaining high-quality visual outcomes.