用一张图就能改3D模型局部形状，还支持渐变过渡。
3DMorph: Single-Image-Guided Local 3D Shape Editing and Morphing
- 输入一张修改后的图片，自动定位3D模型对应区域并转移变化
- 能生成原形到新形之间的中间形态，适合设计探索
- 首次提出图像引导的3D局部编辑基准，效果优于现有方法
尽管3D生成技术取得进展，但对已有形状进行直观编辑仍受限。与图像可使用成熟修复工具不同，通用3D网格缺乏简单有效的局部编辑方法。现有方法多为全局操作、依赖特定领域、需复杂交互或仅关注外观（颜色与纹理）而非几何结构。本文提出3DMorph，一种无需训练的单图像引导局部3D形状编辑与变形框架。给定一张展示期望形状修改的图像，该方法可自动定位相关3D区域，并将2D修改传递至3D，同时保留未修改部分。3DMorph还能生成原始对象与编辑后对象之间的中间形态，促进设计探索。为评估编辑质量，我们构建了Delta3D，一个包含配对真实编辑标注的图像引导局部3D编辑基准。实验表明，3DMorph能将直观的2D编辑转化为高质量3D结果，显著优于当前最先进的生成与编辑方法。
原文摘要 · Abstract (English)
Despite recent progress in 3D generation, intuitive editing of existing shapes remains limited. Unlike images, which benefit from well-established inpainting tools, general 3D objects such as meshes still lack simple and effective methods for local shape editing. Existing approaches are often global, domain-specific, require complex user interaction, or focus on appearance (color and texture) rather than geometry. We introduce 3DMorph, a training-free framework for single-image-guided local 3D shape editing and morphing. Given an edited image showing a desired shape modification, our method automatically localizes the relevant 3D region and transfers 2D modifications to 3D while preserving unmodified areas. 3DMorph also enables intermediate shape generation between the original and edited objects, facilitating design exploration. To benchmark editing quality, we introduce Delta3D, an image-guided local 3D editing benchmark with paired ground-truth edits. Experimental results show that 3DMorph translates intuitive 2D edits into 3D, outperforming state-of-the-art generative and editing methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。