论文标题
扩散-SDF：签名距离功能的条件生成建模
Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions
论文作者
论文摘要
概率扩散模型已实现了图像合成，介入和文本形象任务的最新结果。但是，它们仍处于产生复杂3D形状的早期阶段。这项工作提出了扩散-SDF，这是一种用于形状完成的生成模型，单视重构建和重建实范围的点云。我们使用神经签名的距离函数（SDF）作为我们的3D表示，以通过神经网络的各种信号（例如，点云，2D图像）的几何形状进行参数化。神经SDF是隐式功能，并且扩散它们等于学习其神经网络权重的逆转，我们使用自定义调制模块来解决。广泛的实验表明，我们的方法能够从部分输入中进行现实的无条件产生和条件产生。这项工作将扩散模型的领域从学习2D，显式表示，3D，隐式表示。
Probabilistic diffusion models have achieved state-of-the-art results for image synthesis, inpainting, and text-to-image tasks. However, they are still in the early stages of generating complex 3D shapes. This work proposes Diffusion-SDF, a generative model for shape completion, single-view reconstruction, and reconstruction of real-scanned point clouds. We use neural signed distance functions (SDFs) as our 3D representation to parameterize the geometry of various signals (e.g., point clouds, 2D images) through neural networks. Neural SDFs are implicit functions and diffusing them amounts to learning the reversal of their neural network weights, which we solve using a custom modulation module. Extensive experiments show that our method is capable of both realistic unconditional generation and conditional generation from partial inputs. This work expands the domain of diffusion models from learning 2D, explicit representations, to 3D, implicit representations.
