3DOT: Texture Transfer for 3DGS Objects from a Single Reference Image
Xiao Cao, Beibei Lin, Bo Wang, Zhiyong Huang, Robby T. Tan
摘要
3D texture swapping allows for the customization of 3D object textures, enabling efficient and versatile visual transformations in 3D editing. While no dedicated method exists, adapted 2D editing and text-driven 3D editing approaches can serve this purpose. However, 2D editing requires frame-by-frame manipulation, causing inconsistencies across views, while text-driven 3D editing struggles to preserve texture characteristics from reference images. To tackle these challenges, we introduce 3DSwapping, a 3D texture swapping method that integrates: 1) progressive generation, 2) view-consistency gradient guidance, and 3) prompt-tuned gradient guidance. To ensure view consistency, our progressive generation process starts by editing a single reference image and gradually propagates the edits to adjacent views. Our view-consistency gradient guidance further reinforces consistency by conditioning the generation model on feature differences between consistent and inconsistent outputs. To preserve texture characteristics, we introduce prompt-tuning-based gradient guidance, which learns a token that precisely captures the difference between the reference image and the 3D object. This token then guides the editing process, ensuring more consistent texture preservation across views. Overall, 3DSwapping integrates these novel strategies to achieve higher-fidelity texture transfer while preserving structural coherence across multiple viewpoints. Extensive qualitative and quantitative evaluations confirm that our three novel components enable convincing and effective 2D texture swapping for 3D objects. Code will be available upon acceptance.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- LaS-Comp: Zero-shot 3D Completion with Latent–Spatial ConsistencyWeilong Yan, Li Haipeng, Hao Xu, Nianjin Ye 等CVPR 2026 · 被引用 14 次
- GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image CompletionBeibei Lin, Tingting Chen, Robby T. TanNeurIPS 2025 · 被引用 10 次
它引用的顶会 Paper27
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Emerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou 等ICCV 2021 · 被引用 8,921 次
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 被引用 6,759 次
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan 等CVPR 2022 · 被引用 1,603 次
相关 Paper
- TEXTure: Text-Guided Texturing of 3D ShapesElad Richardson, Gal Metzer, Yuval Alaluf, Raja Giryes 等SIGGRAPH 2023 · 被引用 196 次
- 3D-Aware Face SwappingYixuan Li, Chao Ma, Yichao Yan, Wenhan Zhu 等CVPR 2023
- D2Gaussian: Dynamic Control with Discretized 3D View Modeling for Text-Driven 3D Gaussian Splatting EditingYefei Sheng, Jie Wang, Ming Tao, Bing-Kun BaoACM MM 2025 · 被引用 1 次
- Interp3D: Correspondence-aware Interpolation for Generative Textured 3D MorphingXiaolu Liu, Yicong Li, Qiyuan He, Jiayin Zhu 等ICLR 2026 · 被引用 6 次
- Pro3D-Editor: A Progressive-Views Perspective for Consistent and Precise 3D EditingYang Zheng, Mengqi Huang, Nan Chen, Zhendong MaoNeurIPS 2025 · 被引用 11 次
