Recently, probabilistic denoising diffusion models (DDMs) have greatly advanced the generative power of neural networks. DDMs, inspired by non-equilibrium thermodynamics, have not only been used for 2D image generation, but can also readily be applied to 3D point clouds. However, representing 3D shapes as point clouds has a number of drawbacks, most obvious perhaps that they have no notion of topology or connectivity. Here, we explore an alternative route and introduce tetrahedral diffusion models, an extension of DDMs to tetrahedral partitions of 3D space. The much more structured 3D representation with space-filling tetrahedra makes it possible to guide and regularize the diffusion process and to apply it to colorized assets. To manipulate the proposed representation, we develop tetrahedral convolutions, down- and up-sampling kernels. With those operators, 3D shape generation amounts to learning displacement vectors and signed distance values on the tetrahedral grid. Our experiments confirm that Tetrahedral Diffusion yields plausible, visually pleasing and diverse 3D shapes, is able to handle surface attributes like color, and can be guided at test time to manipulate the resulting shapes.
翻译:最近,概率分解扩散模型(DDMM ) 大幅提升了神经网络的遗传力。 DDDM在非平衡性热热动力学的非平衡性热动力学的启发下,不仅用于2D图像生成,而且可以很容易地应用于3D点云。不过,作为点云的3D形状代表了3D形状,有许多缺点,最明显的可能是它们没有表层学或连接的概念。在这里,我们探索了替代路线,并引入了四合散扩散模型,将DDDDD扩大到3D空间的四面分点分区。由空间填充四希德空间的更结构化的3D代表系统不仅用于2D图像生成,还可用于2D图像生成,而且可以很容易地适用于3D点云云云云云云云云云云云云云云云云云,为了操纵拟议的代表,我们开发四四相相相相相曲线、下游和上上上下、上上下、上上下、上下、上下、上下标的内导、下、下、下、下、下、上方的内导3D、下、下、下、下、下、下、下、下、下、下、下、上接接操作操作操作操作操作操作的骨、,能够操作操作操作操作的3D、上操作操作操作操作操作操作操作操作操作操作的3D的3D的3D的3D。3D的3D的骨、可以操作操作操作操作操作操作操作操作操作操作操作操作操作操作操作操作操作操作操作操作操作操作操作操作操作者、3D的3D的3D的3D的3D的3D的3D的3D的骨、制的骨、制、下、下、下、下、下、下、下、下、下、下、下、下、下、下、上,可以到操作、下、下、下、下、下、下、下、下、下、下、下、上操作、上操作、上、上、上操作、上操作、上操作、上操作、上操作、上、上、上、上操作、上操作、上操作、上操作、上操作、制產、制、上操作、上操作、制、制、制、制、制、制、制、