Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909455108538368 |
|---|---|
| author | Liang, Li Akhtar, Naveed Vice, Jordan Kong, Xiangrui Mian, Ajmal Saeed |
| author_facet | Liang, Li Akhtar, Naveed Vice, Jordan Kong, Xiangrui Mian, Ajmal Saeed |
| contents | 3D semantic scene completion is critical for multiple downstream tasks in autonomous systems. It estimates missing geometric and semantic information in the acquired scene data. Due to the challenging real-world conditions, this task usually demands complex models that process multi-modal data to achieve acceptable performance. We propose a unique neural model, leveraging advances from the state space and diffusion generative modeling to achieve remarkable 3D semantic scene completion performance with monocular image input. Our technique processes the data in the conditioned latent space of a variational autoencoder where diffusion modeling is carried out with an innovative state space technique. A key component of our neural network is the proposed Skimba (Skip Mamba) denoiser, which is adept at efficiently processing long-sequence data. The Skimba diffusion model is integral to our 3D scene completion network, incorporating a triple Mamba structure, dimensional decomposition residuals and varying dilations along three directions. We also adopt a variant of this network for the subsequent semantic segmentation stage of our method. Extensive evaluation on the standard SemanticKITTI and SSCBench-KITTI360 datasets show that our approach not only outperforms other monocular techniques by a large margin, it also achieves competitive performance against stereo methods. The code is available at https://github.com/xrkong/skimba |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_07260 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion Liang, Li Akhtar, Naveed Vice, Jordan Kong, Xiangrui Mian, Ajmal Saeed Computer Vision and Pattern Recognition Artificial Intelligence 3D semantic scene completion is critical for multiple downstream tasks in autonomous systems. It estimates missing geometric and semantic information in the acquired scene data. Due to the challenging real-world conditions, this task usually demands complex models that process multi-modal data to achieve acceptable performance. We propose a unique neural model, leveraging advances from the state space and diffusion generative modeling to achieve remarkable 3D semantic scene completion performance with monocular image input. Our technique processes the data in the conditioned latent space of a variational autoencoder where diffusion modeling is carried out with an innovative state space technique. A key component of our neural network is the proposed Skimba (Skip Mamba) denoiser, which is adept at efficiently processing long-sequence data. The Skimba diffusion model is integral to our 3D scene completion network, incorporating a triple Mamba structure, dimensional decomposition residuals and varying dilations along three directions. We also adopt a variant of this network for the subsequent semantic segmentation stage of our method. Extensive evaluation on the standard SemanticKITTI and SSCBench-KITTI360 datasets show that our approach not only outperforms other monocular techniques by a large margin, it also achieves competitive performance against stereo methods. The code is available at https://github.com/xrkong/skimba |
| title | Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2501.07260 |