ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space
- Published
- Source
- arXiv
- Paper number
- 604
- Field
- Computer Vision
- arXiv ID
- 2607.11673
Key points
- SGP, a single representation combining panorama and point cloud, processes all input modalities in a unified way.
- We improve 3D consistency in a 14B VACE-based panorama video generator through 3DRL post-training.
- Rich inputs, including multi-view and video, are handled through a strict geometric pipeline to minimize hallucination.
- An iterative FLUX-based repair module resolves panorama resolution limits and view mismatches.
- The ABot-3DGS data engine generates fully aligned training data of RGB, point maps, and poses.
- It supports indoor, outdoor, and aerial domains in a single pipeline and can be linked with mapped POIs.
Paper links
External research summaries. These are not HDATF publications or measured product results.