Author

Homanga Bharadhwaj

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

MotionForesight: Re-purposing Video Models for Future 3D Scene-Flow Prediction

This work studies how to learn anticipation of how objects move during human-object interaction from ordinary monocular videos of human-object interaction, and shows that it can efficiently re-purpose video priors into explicit geometric forecasts for embodied intelligence.

Homanga Bharadhwaj, Yash Jangir · 0 citations