Paper Detail
Wangbo Yu, Kunhao Liu, Wenbo Hu, Shenghai Yuan, Chaoran Feng, Haiyang Zhou, Yukun Huang, Yiran Wang, Wang Zhao, Yingmin Luo, Ying Shan
Video world models enable interactive exploration of dynamic environments, yet struggle to respect prior observations over long horizons and across viewpoints. We present WorldCrafter, a video world model that learns a camera-queryable implicit 3D-aware memory for this purpose. The key insight is to let the requested viewpoint shape how multi-view evidence is compressed into the video generator's limited token budget. Trained jointly with the video generator, a memory encoder and pose-conditioned readout module integrate historical observations into a fixed set of target view-specific tokens before denoising, without explicit depth-based correspondences. By combining this memory with recent temporal context and few-step distillation, WorldCrafter enables streaming scene exploration from a single input image or text prompt. Experiments across static and dynamic scenes show substantial gains in long-horizon consistency and camera-control accuracy while preserving visual quality during minute-scale exploration.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{yu2026worldcrafter,
title = {WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory},
author = {Wangbo Yu and Kunhao Liu and Wenbo Hu and Shenghai Yuan and Chaoran Feng and Haiyang Zhou and Yukun Huang and Yiran Wang and Wang Zhao and Yingmin Luo and Ying Shan},
year = {2026},
abstract = {Video world models enable interactive exploration of dynamic environments, yet struggle to respect prior observations over long horizons and across viewpoints. We present WorldCrafter, a video world model that learns a camera-queryable implicit 3D-aware memory for this purpose. The key insight is to let the requested viewpoint shape how multi-view evidence is compressed into the video generator's limited token budget. Trained jointly with the video generator, a memory encoder and pose-conditione},
url = {https://arxiv.org/abs/2609.24984},
keywords = {cs.CV, cs.AI, cs.GR, code available, huggingface daily},
eprint = {2609.24984},
archiveprefix = {arXiv},
}
{}