الملخص
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.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Yu, W., Liu, K., Hu, W., Yuan, S., Feng, C., Zhou, H., Huang, Y., Wang, Y., Zhao, W., Luo, Y., & Shan, Y. (2026). WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory. https://omanscience.com/ar/articles/worldcrafter-consistent-video-world-model-with-implicit-3d-aware-memory
MLA 9
Yu, Wangbo, et al. "WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory." https://omanscience.com/ar/articles/worldcrafter-consistent-video-world-model-with-implicit-3d-aware-memory.
شيكاغو (المؤلف–التاريخ)
Yu, Wangbo, Kunhao Liu, Wenbo Hu, Shenghai Yuan, Chaoran Feng, Haiyang Zhou, Yukun Huang, Yiran Wang, Wang Zhao, Yingmin Luo, and Ying Shan. 2026. "WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory." https://omanscience.com/ar/articles/worldcrafter-consistent-video-world-model-with-implicit-3d-aware-memory.
هارفارد
Yu, W., Liu, K., Hu, W., Yuan, S., Feng, C., Zhou, H., Huang, Y., Wang, Y., Zhao, W., Luo, Y. and Shan, Y. (2026) 'WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory', Available at: https://omanscience.com/ar/articles/worldcrafter-consistent-video-world-model-with-implicit-3d-aware-memory.
فانكوفر
Yu W, Liu K, Hu W, Yuan S, Feng C, Zhou H, et al. WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory. https://omanscience.com/ar/articles/worldcrafter-consistent-video-world-model-with-implicit-3d-aware-memory
IEEE
W. Yu, K. Liu, W. Hu, S. Yuan, C. Feng, H. Zhou, Y. Huang, Y. Wang, W. Zhao, Y. Luo, and Y. Shan, "WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory," https://omanscience.com/ar/articles/worldcrafter-consistent-video-world-model-with-implicit-3d-aware-memory.