Learning Foresight without Explicit Trajectories for 3D Diffusion Policies

Paper recorded by Signals 4 on 2026-09-17 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-17 on arXiv · recorded by Signals 4 on 2026-09-18

Category: cs.CV · 计算机视觉 · first seen 2026-09-18

Abstract

3D diffusion policies are strong at generating geometrically grounded actions from current observations, but successful manipulation requires not only knowing what motion is feasible now, but also anticipating where the interaction is heading. Existing policies largely leave such foresight to emerge implicitly from action learning. We introduce Movement Trend Guidance, a simple but effective way t

Read on arXiv →