Preprint
Aug 2026
Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models
This work replaces the static critic with a feed-forward 4D reconstruction reward that explicitly models scene dynamics, allowing coherent motion to receive high consistency rewards, and adds a motion prior that rewards natural scene-flow magnitude while penalizing jitter and non-rigid artifacts.
Yuanhao Ban, Jiaqi Feng, Hengguang Zhou et al.
· 0 citations