MotionForesight: Re-purposing Video Models for Future 3D Scene-Flow Prediction
Humans can infer how objects are likely to move from passive observation: a cup may be lifted, a drawer may slide, and a lid may rotate shut. Such predictions expose the physical consequences of interaction needed to act in the real world. We study how to learn this anticipation from ordinary monocular videos of human-object interaction. Given a short observed video context, MotionForesight predicts future 3D trajectories for points on the manipulated object. This casts interaction prediction as object-centered 3D motion forecasting without any assumptions on the object properties. Our key ins
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%Developer-Y/cs-video-courses →
“Fuzzy title match (0.73): “MotionForesight: Re-purposing Video Models for Future 3D Sce” ≈ “Developer-Y/cs-video-courses””
- LinkedLinked via arxiv author · 85%Homanga Bharadhwaj →
“MotionForesight: Re-purposing Video Models for Future 3D Scene-Flow Prediction”
- LinkedLinked via arxiv author · 85%Yash Jangir →
“MotionForesight: Re-purposing Video Models for Future 3D Scene-Flow Prediction”