The paper introduces latent spatial memory, a 3D cache that stores scene information directly in diffusion latent space, eliminating the need for pixel-space reconstruction. It presents Mirage, a framework that lifts latent tokens into 3D using depth-guided back‑projection and queries the memory via latent‑space warping, achieving significant speed and memory gains. Experiments demonstrate up to 10.57× faster video generation, a 55× reduction in memory usage, and state‑of‑the‑art performance on WorldScore and strong reconstruction on RealEstate10K.
By Weijie Wang, Haoyu Zhao, Yifan Yang, Feng Chen, Zeyu Zhang, Yefei He, Zicheng Duan, Donny Y. Chen, Yuqing Yang, Bohan Zhuang
arXiv:2609.35734v2 Announce Type: replace
Abstract: Novel view synthesis from sparse images must reconcile faithful reconstruction of observed regions with plausible completion of unseen content, whi...
By Kerui Ren, Tao Lu, Linning Xu, Changjian Jiang, Mu Huang, Chunhua Shen, Mulin Yu, Bo Dai
arXiv:2608. 13492v1 Announce Type: new Abstract: This report presents an improved version of AlayaWorld.
By AlayaWorld Team, Kaipeng Zhang, Chuanhao Li, Yifan Zhan, Yongtao Ge, Yuanyang Yin, Jiaming Tan, Kang He, Liaoyuan Fan, Mingliang Zhai, Ruicong Liu, Xiaojie Xu, Xuangeng Chu, Zhen Li, Zhengyuan Lin, Zhixiang Wang, Zian Meng, Zihui Gao
arXiv:2603. 03482v2 Announce Type: replace-cross Abstract: Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities.
By Samuel Garcin, Thomas Walker, Steven McDonagh, Tim Pearce, Hakan Bilen, Tianyu He, Kaixin Wang, Jiang Bian
Reconstructing 3D scenes from a single image is a fundamental challenge in computer vision, with broad applications in virtual reality, robotics, and content creation. Recent methods achieve outstanding performance by leveraging camera-controlled video diffusion models, but rely on iterative diffusion sampling, which greatly limits their practical deployment.
4D generation synthesizes dynamic 3D scenes from conditions such as text or images. Existing methods either reconstruct generated RGB videos with a separate 4D model or adapt a particular video generator to predict geometry directly.