Although the recent rapid evolution of 3D generative neural networks greatly improves 3D shape generation, it is still not convenient for ordinary users to create 3D shapes and control the local geometry of generated shapes. To address these challenges, we propose a diffusion-based 3D generation framework -- locally attentional SDF diffusion, to model plausible 3D shapes, via 2D sketch image input. Our method is built on a two-stage diffusion model. The first stage, named occupancy-diffusion, aims to generate a low-resolution occupancy field to approximate the shape shell. The second stage, named SDF-diffusion, synthesizes a high-resolution signed distance field within the occupied voxels determined by the first stage to extract fine geometry. Our model is empowered by a novel view-aware local attention mechanism for image-conditioned shape generation, which takes advantage of 2D image patch features to guide 3D voxel feature learning, greatly improving local controllability and model generalizability. Through extensive experiments in sketch-conditioned and category-conditioned 3D shape generation tasks, we validate and demonstrate the ability of our method to provide plausible and diverse 3D shapes, as well as its superior controllability and generalizability over existing work. Our code and trained models are available at https://zhengxinyang.github.io/projects/LAS-Diffusion.html

翻译：尽管近期三维生成神经网络的快速发展极大提升了三维形状生成能力，但普通用户仍难以便捷地创建三维形状并控制生成形状的局部几何结构。为解决这些挑战，我们提出基于扩散的三维生成框架——局部注意力SDF扩散，通过二维草图图像输入对合理三维形状进行建模。该方法建立在两阶段扩散模型基础上：第一阶段名为占有扩散，旨在生成低分辨率占有场以近似形状外壳；第二阶段名为SDF扩散，在由第一阶段确定的占有体素内合成高分辨率有符号距离场以提取精细几何。模型由新型视图感知局部注意力机制赋能，该机制利用二维图像块特征引导三维体素特征学习，极大提升了局部可控性与模型泛化能力。通过在草图引导与类别引导的三维形状生成任务上的大量实验，我们验证并展示了该方法生成合理多样三维形状的能力，以及相较于现有工作在可控性与泛化性方面的显著优势。代码与训练模型可在https://zhengxinyang.github.io/projects/LAS-Diffusion.html获取。