Research Papers

This paper introduces a SLAM framework that achieves real-time CPU-only performance in dense, registration-error-minimization-based odometry and mapping by leveraging exact point cloud downsampling via coreset extraction, eliminating the need for

MP-SfM redefines classical Structure-from-Motion by tightly integrating monocular depth and surface normal priors into incremental SfM, enabling robust 3D reconstruction from sparse, unstructured image collections. Key Highlights: Resources Paper: https://arxiv.org/abs/2504.20040Github:

NormalCrafter introduces a novel approach for surface normal estimation in videos, leveraging diffusion priors to achieve high spatial fidelity and temporal consistency over arbitrary-length sequences. Key Highlights: Project Related articles

OpenLiDARMap presents a GNSS-free mapping framework that combines sparse public map priors with LiDAR data through scan-to-map and scan-to-scan alignment. This approach achieves georeferenced and drift-free point cloud maps. Key

 MedSAM2 introduces a robust foundation model for promptable segmentation in 3D medical images and temporal video data, built by fine-tuning SAM2.1 on a large-scale curated medical dataset. Key Highlights: Resources

GenZ-ICP introduces an innovative iterative Closest Point (ICP) method that enhances LiDAR-based pose estimation by adaptively integrating point-to-plane and point-to-point error metrics, ensuring robust performance across diverse and degenerative environments.