Preprint
Sep 2026
OctWorld: Long-Range World-Consistent Video Generation with Octree-Based 3D Mapping
We present OctWorld, a video diffusion framework with persistent 3D memory for generating explorable, world-consistent, and high-fidelity visual scenes. Given a single image, OctWorld performs stable autoregressive world generation along user-specified camera trajectories. We focus on long-range generation, characteriz...
Ze-Long Lv, Si-Cheng Xu, Jianfeng Xiang et al.
· 1 citation