 | Ganlin Zhang, Shenhan Qian, Xi Wang, Daniel Cremers Preprint on ArXiv, 2025 Github Repo (Coming Soon) | ArXiv | Project website ViSTA-SLAM is a real-time monocular dense SLAM pipeline that combines a Symmetric Two-view Association (STA) frontend with Sim(3) pose graph optimization and loop closure, enabling accurate camera trajectories and high-quality 3D scene reconstruction from RGB inputs. |
 | Weirong Chen, Ganlin Zhang, Felix Wimbauer, Rui Wang, Nikita Araslanov, Andrea Vedaldi, Daniel Cremers ICCV 2025 (oral) Github Repo (Coming Soon) | ArXiv | Project website A method for consistent dynamic scene reconstruction via motion decoupling, bundle adjustment, and global refinement. |
 | Erik Sandström*, Ganlin Zhang*, Keisuke Tateno, Michael Oechsle, Youmin Zhang, Manthan Patel, Luc Van Gool, Martin R. Oswald, Federico Tombari CVPRW 2025 Github Repo | Paper | Supp We use a keyframe based frame to frame tracker based on dense optical flow connected to a pose graph for global consistency. For dense mapping, we resort to a 3DGS representation, suitable for extracting both dense geometry and rendering from. |
 | Ganlin Zhang*, Erik Sandström*, Youmin Zhang, Manthan Patel, Luc Van Gool, Martin R. Oswald Preprint on ArXiv, 2024 Github Repo | ArXiv | Project website 1. A monocular SLAM pipeline with deformable neural point cloud scene representation. 2. Novel DSPO layer for BA, which can jointly optimize depth map, depth scale, and camera pose. |
 | Ganlin Zhang, Viktor Larsson, Daniel Barath CVPR 2023 Github Repo | ArXiv 1. Better model the underlying noise distributions by directly propagating the uncertainty from the point correspondences into the rotation averaging. 2. Integrate a variant of the MAGSAC++ loss into the rotation averaging, instead of using the classical robust losses. |