A method for consistent dynamic scene reconstruction via motion decoupling, bundle adjustment, and global refinement.

A method for learning camera poses and intrinsics from dynamic casual videos.

Dynamic radiance field reconstruction from only two images, enabled by object-level bundle adjustment.

A robust visual odometry system leveraging temporal context with long-term point tracking to tackle occlusions and dynamic environments.

A visual localization pipeline using rendered data from NeRF, uncertainty-guided novel view selection, and evidential scene coordinate regression.

An accurate and reliable pipeline for dense two-view SfM using weighted bundle adjustment with robust outlier filtering and learning-based confidence modeling.

Webly supervised learning for semantic label confusion using visual-semantic graph with metadata-aware anchor selection and GNN-based label propagation.

Webly supervised learning for noisy label classification via sample-wise web label correction with model confidence and pseudo machine label.

A robust and highly-extensible Python SLAM built on pycolmap; achieved better pose accuracy and significant speed improvement compared to COLMAP.

A general neural rendering pipeline for photorealistic synthesis in VR devices in real-time; demo included human neural rendering and scene style transfer.