Composing two optical flows to supervise a third yields an architecture-agnostic geometric training constraint that consistently improves optical flow across supervised, unsupervised, and transfer settings.
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
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.
citing papers explorer
-
Triangular Consistency as a Universal Constraint for Learning Optical Flow
Composing two optical flows to supervise a third yields an architecture-agnostic geometric training constraint that consistently improves optical flow across supervised, unsupervised, and transfer settings.
-
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.