5 papers
Look Up and Look Back: Hidden Attention and Latent Orientation in a Frozen Foundation Model for Panoramic SLAM
Zhuang Xiong, Guohao Zhang, Chen Zhang +4
Monocular panoramic SLAM benefits from substantial visual overlap under large camera rotations, yet remains prone to errors caused by camera tilt, scale drift, and false loop closu…
VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency
Zhuang Xiong, Chen Zhang, Qingshan Xu +1
Despite recent progress in calibration-free monocular SLAM via 3D vision foundation models, scale drift remains severe on long sequences. Motion-agnostic partitioning breaks contex…
PSDF: Prior-Driven Neural Implicit Surface Learning for Multi-view Reconstruction
Wanjuan Su, Chen Zhang, Qingshan Xu +1
Surface reconstruction has traditionally relied on the Multi-View Stereo (MVS)-based pipeline, which often suffers from noisy and incomplete geometry. This is due to that although…
PR-NeuS: A Prior-based Residual Learning Paradigm for Fast Multi-view Neural Surface Reconstruction
Jianyao Xu, Qingshan Xu, Xinyao Liao +4
Neural surfaces learning has shown impressive performance in multi-view surface reconstruction. However, most existing methods use large multilayer perceptrons (MLPs) to train thei…
PG-NeuS: Robust and Efficient Point Guidance for Multi-View Neural Surface Reconstruction
Chen Zhang, Wanjuan Su, Qingshan Xu +1
Recently, learning multi-view neural surface reconstruction with the supervision of point clouds or depth maps has been a promising way. However, due to the underutilization of pri…