Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion (AAAI 2025)

Li Liang¹, Naveed Akhtar², Jordan Vice¹, Xiangrui Kong¹, Ajmal Mian¹,

¹The University of Western Australia
²The University of Melbourne

Figure 1: Schematics of the approach. Our method comprises a 3D scene completion and a 3D semantic segmentation network. The former is encapsulated in a VAE framework that employs two sub-networks for conditioning its latent space, a Muti-Scale Convolutonal Block (MSCB) and a Skimba denoising network. The 3D semantic segmentation network employs a variant of Skimba. L, W, and H denote the length, width, and height of the original scene, and D is feature map dimension.

Figure 2: Architectural details of the Skimba denoising network. Refer to the text for details.

We will release the code soon.