OctWorld: Long-Range World-Consistent Video Generation with Octree-Based 3D Mapping

2026-09-03

AI Summary

OctWorld通过引入基于八叉树的3D映射OctMap，解决了长距离视频生成中保持空间一致性的难题，实现高保真、可探索的视觉场景自动生成。

Abstract

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, characterized by extended camera paths and wide viewpoint coverage, where preserving spatial consistency is particularly challenging when previously generated regions are revisited. To address this problem, we introduce OctMap, an extensible and spatially adaptive 3D memory that progressively fuses generated visual observations and their corresponding depth maps into a global representation. OctMap employs TSDF fusion within a dynamic sparse octree whose spatial resolution adapts to image evidence. This design preserves geometric and appearance details across diverse scene scales while maintaining low memory overhead. Experiments demonstrate that OctWorld generates long-range, spatially consistent videos and outperforms prior methods on both existing benchmarks and challenging long-range generation settings. OctMap also provides clear advantages over point-based caches and fixed-resolution TSDF volumes. Project page: https://maxtirerror.github.io/octworldpage/

Problem

• Long-Range Generation
• Spatial Consistency
• 3D Memory

Innovation

• OctWorld
• OctMap
• TSDF fusion
• spatially adaptive 3D memory
• long-range generation