{"slug": "point-diffusion-mamba-unified-diffusion-state-space-modeling-for-single-view-3d", "title": "Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity", "summary": "Researchers proposed Point Diffusion Mamba (PDM), a method that combines diffusion models with state-space modeling for single-view 3D reconstruction under data-scarce conditions, according to an arXiv paper (arXiv:2609.25538v1). PDM pairs a Local Geometric Aggregation module with Mamba blocks and adds a Hierarchical Feature Integration Network and a Dynamic Weighted Sampling strategy, and experiments on the ShapeNet and Pix3D benchmarks show it outperforms state-of-the-art methods. Code is available at https://github.com/NWUzhouwei/PDM.", "body_md": "arXiv:2609.25538v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/point-diffusion-mamba-unified-diffusion-state-space-modeling-for-single-view-3d", "canonical_source": "https://arxiv.org/abs/2609.25538", "published_at": "2026-09-23 04:00:00+00:00", "updated_at": "2026-09-23 04:27:22.345533+00:00", "lang": "en", "topics": ["computer-vision", "generative-ai", "machine-learning", "ai-research"], "entities": ["Point Diffusion Mamba", "Mamba", "ShapeNet", "Pix3D", "arXiv", "Hierarchical Feature Integration Network", "Local Geometric Aggregation"], "alternates": {"html": "https://wpnews.pro/news/point-diffusion-mamba-unified-diffusion-state-space-modeling-for-single-view-3d", "markdown": "https://wpnews.pro/news/point-diffusion-mamba-unified-diffusion-state-space-modeling-for-single-view-3d.md", "text": "https://wpnews.pro/news/point-diffusion-mamba-unified-diffusion-state-space-modeling-for-single-view-3d.txt", "jsonld": "https://wpnews.pro/news/point-diffusion-mamba-unified-diffusion-state-space-modeling-for-single-view-3d.jsonld"}}