Real-time 3D scene reconstruction from monocular images using sparse points from SLAM with SST
Real-time 3D scene reconstruction from monocular images using sparse points from SLAM with SST
SST: Real-time End-to-end Monocular 3D Reconstruction via Sparse Spatial-Temporal Guidance
arXiv paper abstract https://arxiv.org/abs/2212.06524
arXiv PDF paper https://arxiv.org/pdf/2212.06524.pdf
Real-time monocular 3D reconstruction is a challenging problem that remains unsolved.
Although recent ... methods have ... promising results, tiny structures and geometric boundaries are hardly captured
... propose an end-to-end 3D reconstruction network SST, which utilizes Sparse estimated points from visual SLAM system as ... Spatial guidance and fuses Temporal features via a novel cross-modal attention mechanism, achieving more detailed reconstruction results.
... propose a Local Spatial-Temporal Fusion module to exploit ... spatial-temporal cues from multi-view color information and sparse priors, as well a Global Spatial-Temporal Fusion module to refine the local TSDF volumes ... from coarse to fine.
... demonstrate that SST outperforms all state-of-the-art competitors, whilst keeping a high inference speed at 59 FPS, enabling real-world applications with real-time requirements.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments