机构
*
Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
;
SSE, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)理工学院)
;
Pinscreen
LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models
LaVR:基于大规模4D重建模型的场景潜在条件生成视频轨迹重绘
Mingyang Xie, Numair Khan, Tianfu Wang, Naina Dhingra, Seonghyeon Nam, Haitao Yang, Zhuo Hui, Christopher Metzler, Andrea Vedaldi, Hamed Pirsiavash, Lei Luo
机构
*
Meta
;
University of Maryland(马里兰大学)
;
University of Oxford(牛津大学)
;
UC Davis(加州大学戴维斯分校)
Any4D: Open-Prompt 4D Generation from Natural Language and Images
Any4D: 从自然语言和图像生成开放提示的4D生成
Hao Li, Qiao Sun
专题命中
视频生成
:video generation(abstract);分类 cs.CV
AI总结
本文提出Primitive Embodied World Models,通过限制视频生成时间范围,实现语言与视觉表示的细粒度对齐,降低学习复杂度,提升数据效率,并减少推理延迟,支持复杂任务的组合泛化。
CommentsThe authors identified issues in the 4D generation pipeline and evaluation that affect result validity. To ensure scientific accuracy, we will revise the methodology and experiments thoroughly before resubmitting. This version should not be cited or relied upon
机构
*
Texas A&M University(德克萨斯A&M大学)
;
University of Minnesota(明尼苏达大学)
;
University of Wisconsin–Madison(威斯康星大学麦迪逊分校)
;
University of California, Los Angeles(加州大学洛杉矶分校)
;
University of Texas at Austin(得克萨斯大学奥斯汀分校)
;
Amazon(亚马逊)
;
State University of New York at Stony Brook(纽约州立大学石溪分校)