Abstract
While single-view 3D reconstruction has seen significant progress, extrapolating complex 3D structures from inherently ambiguous 2D observations remains fundamentally ill-posed, particularly in the critically underexplored data-scarce regime. To address this challenge, we propose Point Diffusion Mamba (PDM), a method that integrates the generative power of diffusion models with the efficiency of state-space model for single-view 3D reconstruction under data-scarce conditions. Specifically, PDM employs a lightweight reconstruction module tailored to handle unordered point-cloud inputs effectively. By combining a Local Geometric Aggregation module with Mamba blocks, our approach jointly models global geometric structures and local details. In 3D reconstruction, each point in the initial noisy input requires a precise prediction, yet the high-level features extracted by the Mamba module capture only abstract semantic information from sparse points. To bridge this gap, we introduce the Hierarchical Feature Integration Network, which fuses high-level semantic and local geometric features for each point, overcoming the limitations of token-based point-cloud reconstruction. Furthermore, we propose a Dynamic Weighted Sampling strategy that adaptively unifies 3D generation with single-view reconstruction by leveraging generative priors to enhance reconstruction quality. Experimental results on the ShapeNet and Pix3D benchmarks demonstrate that PDM outperforms state-of-the-art methods, providing an effective solution for 3D reconstruction under data-scarce settings. Code is available at: https://github.com/NWUzhouwei/PDM.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Zhou, W., Shi, X., Hao, X., Hao, X., Li, K., Peng, J., & He, Y. (2026). Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity. https://omanscience.com/en/articles/point-diffusion-mamba-unified-diffusion-state-space-modeling-for-single-view-3d-reconstruction-under-data-scarcity
MLA 9
Zhou, Wei, et al. "Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity." https://omanscience.com/en/articles/point-diffusion-mamba-unified-diffusion-state-space-modeling-for-single-view-3d-reconstruction-under-data-scarcity.
Chicago (author–date)
Zhou, Wei, Xinzhe Shi, Xingxing Hao, Xing Hao, Kang Li, Jinye Peng, and Ying He. 2026. "Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity." https://omanscience.com/en/articles/point-diffusion-mamba-unified-diffusion-state-space-modeling-for-single-view-3d-reconstruction-under-data-scarcity.
Harvard
Zhou, W., Shi, X., Hao, X., Hao, X., Li, K., Peng, J. and He, Y. (2026) 'Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity', Available at: https://omanscience.com/en/articles/point-diffusion-mamba-unified-diffusion-state-space-modeling-for-single-view-3d-reconstruction-under-data-scarcity.
Vancouver
Zhou W, Shi X, Hao X, Hao X, Li K, Peng J, et al. Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity. https://omanscience.com/en/articles/point-diffusion-mamba-unified-diffusion-state-space-modeling-for-single-view-3d-reconstruction-under-data-scarcity
IEEE
W. Zhou, X. Shi, X. Hao, X. Hao, K. Li, J. Peng, and Y. He, "Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity," https://omanscience.com/en/articles/point-diffusion-mamba-unified-diffusion-state-space-modeling-for-single-view-3d-reconstruction-under-data-scarcity.