mlsanityData to 14 Oct 2026

3D Stylization via Large Reconstruction Model

arXiv 2504.21836 ↗First posted 30 Apr 2025cs.CVcited by 8

Not on the map. Why?

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.

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

40 of 55 references.

References · 40

  1. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  2. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  3. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  4. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  5. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,351
  6. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  7. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  8. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  9. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  10. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 521
  11. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
  12. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
28 more
  1. 2017Universal Style Transfer via Feature Transformscited by 354
  2. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  3. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  4. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  5. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  6. 2024InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generationcited by 170
  7. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 139
  8. 2023Cross-Image Attention for Zero-Shot Appearance Transfercited by 136
  9. 2020Self-supervised Single-view 3D Reconstruction via Semantic Consistencycited by 127
  10. 2023RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Modelscited by 114
  11. 2022Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learningcited by 93
  12. 2020Shape and Viewpoint without Keypointscited by 92
  13. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 89
  14. 2024StyleGaussian: Instant 3D Style Transfer with Gaussian Splattingcited by 79
  15. 2020Leveraging 2D Data to Learn Textured 3D Mesh Generationcited by 69
  16. 2024Visual Style Prompting with Swapping Self-Attentioncited by 63
  17. 2019A Closed-form Solution to Universal Style Transfercited by 42
  18. 2024AID: Attention Interpolation of Text-to-Image Diffusioncited by 25
  19. 2024EASI-Tex: Edge-Aware Mesh Texturing from Single Imagecited by 20
  20. 2021View Generalization for Single Image Textured 3D Modelscited by 19
  21. 2024Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Imagescited by 16
  22. 2022Fine Detailed Texture Learning for 3D Meshes with Generative Modelscited by 15
  23. 2024MatAtlas: Text-driven Consistent Geometry Texturing and Material Assignmentcited by 14
  24. 2024NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFscited by 11
  25. 2023Progressive Learning of 3D Reconstruction Network from 2D GAN Datacited by 10
  26. 2024G-Style: Stylized Gaussian Splattingcited by 5
  27. 2024Surface-aware Mesh Texture Synthesis with Pre-trained 2D CNNscited by 3
  28. 2025MD-ProjTex: Texturing 3D Shapes with Multi-Diffusion Projectioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2025Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Stylescited by 4
  2. 2026VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Imagecited by 4
  3. 2025Jigsaw3D: Disentangled 3D Style Transfer via Patch Shuffling and Maskingcited by 1
  4. 2026DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglementcited by 1
  5. 2025StyleFusion360: View-Consistent Head Stylization via Adaptive Style Modulationcited by 0
  6. 2026SIC3D: Style Image Conditioned Text-to-3D Gaussian Splatting Generationcited by 0
  7. 2026Owner3D: Ownership-Guided Style Writing for Training-Free Localized 3D Stylizationcited by 0
  8. 2026OrnaStyler: Ornament-Aware Latent Editing for Content-Preserving 3D Stylizationcited by 0