OctWorld is a video diffusion framework that uses a persistent 3D memory called OctMap to generate long‑range, world‑consistent videos from a single image. OctMap fuses visual observations and depth maps into a dynamic sparse octree, adapting spatial resolution to image evidence while keeping memory usage low. Experiments show that OctWorld produces spatially consistent videos over extended camera paths and outperforms previous methods on both standard benchmarks and challenging long‑range scenarios.
By Zelong Lv, Sicheng Xu, Jianfeng Xiang, Ruicheng Wang, Yue Dong, Yu Deng, Guangzhong Sun, Jiaolong Yang
WorldWeave is a framework that separates world-state maintenance from visual rendering to enable persistent geometric memory in video generation. It uses diffusion-based image outpainting to create continuous elevation maps, an agent that plans and stitches scenes hierarchically, and a read-only interface that queries world geometry for depth-guided video synthesis. This design allows the world to expand continually without predefined boundaries while preserving consistent structure across camera trajectories and revisits.
By Yifan Huang, Lifan Jiang, Qingyue Hao, Cheng Chen, Boxi Wu, Xiaoxue Ren, Xiaofei He, Dehai Zhao
Persistent Planar Memory for Video World Models (PPMem) introduces a compact 3D memory system using plane primitives for video world models. By integrating a planar prediction head and Depth Token Fusion into a video diffusion transformer, PPMem jointly generates RGB video and planar geometry, merging them into a persistent plane memory that conditions future video chunks. The resulting memory is highly compact, geometrically explicit, cross-view consistent, and adaptive, outperforming prior 3D-grounded models on DL3DV and RealEstate10K in video quality and depth/normal accuracy.
By Yuze He, Bin Tan, Zelin Gao, Yujun Shen, Yong-Jin Liu, Nan Xue, Yinghao Xu
EvoWorld is a world model that generates panoramic video from a single image by combining a video generator with fine‑grained view control, a feedforward transformer that evolves an explicit 3D reconstruction, and a synthesis step that conditions on geometric reprojections from this evolving 3D memory. The model uses the evolving 3D reconstruction as spatial guidance, projecting geometry onto target viewpoints to provide rich spatial cues that improve visual realism and geometric consistency. A new benchmark covering synthetic outdoor, Habitat indoor, and real‑world scenarios evaluates long‑range exploration, loop‑closure detection, and spatial coherence, showing that EvoWorld’s evolving 3D memory enhances visual fidelity and scene coherence over existing methods.
By Jiahao Wang, Luoxin Ye, TaiMing Lu, Junfei Xiao, Jiahan Zhang, Yuxiang Guo, Xijun Liu, Rama Chellappa, Cheng Peng, Alan Yuille, Jieneng Chen
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
Recent video world models have increasingly adopted 3D memory mechanisms to integrate historical observations into a lightweight and persistent scene representation. This naturally raises a complement...
arXiv:2512. 02473v2 Announce Type: replace-cross Abstract: Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations and navigation actions.
By Yuta Oshima, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta
arXiv:2605.12957v2 Announce Type: replace
Abstract: Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of do...
By Hanxin Zhu, Cong Wang, Peiyan Tu, Jiayi Luo, Tianyu He, Xin Jin, Zhibo Chen
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
SpatialCrafter introduces a two‑stage framework for single‑image world modeling that first generates a global 3D proxy using a Point‑anchored Sparse Structure Flow module, then refines appearance with a Generative Deferred Refiner built on a video diffusion model. The method incorporates Parallel Geometry Injection and Proxy‑Aware Corruption training to integrate the proxy without disrupting the pretrained generative manifold, and it is evaluated on a newly constructed dataset of 115K scenes. Experiments demonstrate that SpatialCrafter outperforms existing approaches, reducing long‑term drift and maintaining consistency under rapid camera motion and extreme viewpoints.
By Chuan Fang, Lingteng Qiu, Yixun Liang, Rui Chen, Kunming Luo, Zhaohua Zheng, Tongyuan Bai, Feipeng Tian, Zilong Dong, Zihan Zhou, Ping Tan
Video world models that maintain 3D spatial consistency across generated frames typically rely on explicit point cloud memory constructed in RGB space. This design is both computationally expensive, requiring repeated rendering and VAE encoding, and inherently lossy, as the round trip through pixel space discards rich features of the learned latent representation.
arXiv:2606. 00299v1 Announce Type: cross Abstract: While Video Diffusion Models (VDMs) excel at synthesizing high-fidelity videos, enabling precise camera and scene control remains challenging.
By Jiayi Wu, Haoming Cai, Cornelia Fermuller, Christopher Metzler, Yiannis Aloimonos