用单图引导实现快速3D网格编辑，保留未修改区域细节。
3D Mesh Editing using Masked LRMs
- 通过条件重建模型，仅需一次前向传播完成编辑。
- 在未遮蔽区域保持与顶尖方法相当的几何还原精度。
- 适合需要快速、精细3D修改的设计师或动画师使用。
我们提出一种新型三维形状编辑方法，基于多视角图像的最新三维重建进展。将形状编辑建模为条件重建问题：模型需重建输入形状，但指定的3D区域应根据条件信号生成新几何。为此，我们训练了一个条件大重建模型（LRM），利用随机生成的3D遮挡生成多视角一致的掩码，并以一个干净视角作为条件信号。推理时，手动定义待编辑的3D区域，并提供来自标准视角的编辑图像以填充该区域。实验表明，仅需一次前向传播，该方法不仅在未遮蔽区域实现了与最先进水平相当的重建能力，还具备表达力，能完成多种过去方法难以处理的网格编辑操作，且速度比当前最优方法快2-10倍。
原文摘要 · Abstract (English)
We present a novel approach to shape editing, building on recent progress in 3D reconstruction from multi-view images. We formulate shape editing as a conditional reconstruction problem, where the model must reconstruct the input shape with the exception of a specified 3D region, in which the geometry should be generated from the conditional signal. To this end, we train a conditional Large Reconstruction Model (LRM) for masked reconstruction, using multi-view consistent masks rendered from a randomly generated 3D occlusion, and using one clean viewpoint as the conditional signal. During inference, we manually define a 3D region to edit and provide an edited image from a canonical viewpoint to fill that region. We demonstrate that, in just a single forward pass, our method not only preserves the input geometry in the unmasked region through reconstruction capabilities on par with SoTA, but is also expressive enough to perform a variety of mesh edits from a single image guidance that past works struggle with, while being 2-10x faster than the top-performing prior work.
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。