VideoMDM learns coherent 3D motion manifolds from 2D supervision alone by using a pretrained lifter as noisy teacher, depth-weighted 2D reprojection loss, and adapted regularizers, nearly matching fully 3D-supervised performance on HumanML3D.
A Comprehensive Survey of Visual SLAM Algorithms
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A passage-aware structural mapping approach for RGB-D VSLAM detects doors and openings via joint geometric-semantic-topological fusion and adds passage abstractions to vS-Graphs scene graphs.
citing papers explorer
-
Passage-Aware Structural Mapping for RGB-D Visual SLAM
A passage-aware structural mapping approach for RGB-D VSLAM detects doors and openings via joint geometric-semantic-topological fusion and adds passage abstractions to vS-Graphs scene graphs.