Embody4D generates novel-view videos from monocular robot videos via a 3D-aware synthesis pipeline, confidence-aware expert modulation, and interaction-aware attention for embodied 4D world modeling.
arXiv preprint arXiv:2512.01481 (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
MVTrack4Gen uses multi-view point tracking as geometric and motion supervision for camera-conditioning-only novel-view video diffusion models to improve consistency.
citing papers explorer
-
Embody4D: A Generalist Data Engine for Embodied 4D World Modeling
Embody4D generates novel-view videos from monocular robot videos via a 3D-aware synthesis pipeline, confidence-aware expert modulation, and interaction-aware attention for embodied 4D world modeling.
-
MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation
MVTrack4Gen uses multi-view point tracking as geometric and motion supervision for camera-conditioning-only novel-view video diffusion models to improve consistency.