Demiurge: Forging Navigable 4D Worlds via Autoregressive Video Rerendering
cs.CV
Submitted: 2026-10-10
Updated: 2026-10-10
Project page: https://hanxinzhu-lab.github.io/demiurge_project_page
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- DeepVerse: 4D Autoregressive Video Generation as a World Model
- FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis
- Plenoptic Video Generation
- CameraCtrl: Enabling Camera Control for Text-to-Video Generation
- Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition
- Controllable Video Generation: A Survey
- Yume: An Interactive World Generation Model
- INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling
- Embody4D: A Generalist Data Engine for Embodied 4D World Modeling
- Towards Accurate Generative Models of Video: A New Metric & Challenges
- Wan: Open and Advanced Large-Scale Video Generative Models
- Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels
- CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation
- NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
- ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
- CamI2V: Camera-Controlled Image-to-Video Diffusion Model
- RoboDreamer: Learning Compositional World Models for Robot Imagination
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models