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 with adaptive resolution, preserving geometric and appearance details while keeping memory usage low. Experiments show OctWorld outperforms previous methods on standard benchmarks and challenging long‑range generation tasks.
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
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
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
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
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: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
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:2609.14462v1 Announce Type: new
Abstract: Interactive video world models must maintain broad scene context under camera motion while producing high-fidelity observations with low latency. Exist...
By Jiaming Tan, Mingliang Zhai, Zhen Li, Yuwei Wu, Chuanhao Li, Kaipeng Zhang
AnchorWeave is a memory‑augmented video generation framework that replaces a single misaligned global memory with multiple clean local geometric memories. It retrieves local memories based on coverage of the target trajectory and integrates them through a multi‑anchor weaving controller during generation. Experiments show that this approach improves long‑term scene consistency while preserving visual quality, with ablation studies confirming the benefits of local conditioning, multi‑anchor control, and coverage‑driven retrieval.
By Zun Wang, Han Lin, Jaehong Yoon, Jaemin Cho, Yue Zhang, Mohit Bansal
Puffin-World is a unified multimodal architecture that integrates physical understanding, spatial simulation, and 3D world generation without external offline modules. It jointly models physics, geometry, and appearance as native world states and uses a unified Omni-Camera representation to support diverse tasks and flexible motions. The framework also propagates physical dynamics across future frames, couples appearance and geometry in a single generative process, and scales to complex scenarios with the Puffin-16M dataset of 15 million vision‑language‑camera triplets and 1 million trajectories.
By Kang Liao, Yihang Luo, Xiao-Ming Wu, Linyi Jin, Size Wu, Chunyu Lin, Yao Zhao, Fei Wang, Wei Li, Chen Change Loy
The paper presents a framework that builds a static point cloud prior map from past camera traversals, augmenting each point with DINOv3 semantic features. During runtime, a local prior patch is retrieved, encoded with a sparse voxel backbone, and fused with lifted multi‑view camera features in bird’s‑eye view. This fused representation is then used by sparse transformer heads to predict 3D objects and vectorized map elements, achieving improved performance on Argoverse 2 without requiring LiDAR for prior‑map construction or online inference.
By Markus K\"appeler, Rohit Mohan, Abhinav Valada