Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control

• URL: http://arxiv.org/abs/2606.27964v1
• Date: Fri, 26 Jun 2026 11:08:09 GMT
• Title: Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control
• Abstract summary: "Directing the World" is a fast autoregressive framework for controllable world-model video generation with compositional human-motion and camera-trajectory control.<n>Our key idea is to decouple control learning while preserving a unified autoregressive video prior.<n>For human motion control, we design a t-guided Dynamic Projection mechanism and a refined Motion-CFG strategy.
• Score: 56.828569670698975
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Building interactive world models requires generating realistic videos while maintaining controllable dynamics over long horizons. Autoregressive video generation offers a scalable foundation, but suffers from error accumulation and temporal degradation during extended rollouts. This issue is further amplified under heterogeneous controls such as human motion and camera trajectories, which may interfere and destabilize a pretrained video prior, while existing methods often trade off controllability and visual quality. We propose "Directing the World", a fast autoregressive framework for controllable world-model video generation with compositional human-motion and camera-trajectory control. Our key idea is to decouple control learning while preserving a unified autoregressive video prior. We introduce a Fast-Slow Memory training strategy to stabilize long-horizon rollout learning and improve convergence. For human motion control, we design a t-guided Dynamic Projection mechanism and a refined Motion-CFG strategy, enabling temporally smooth and accurate motion alignment without degrading visual fidelity, and supporting multi-person control.After learning a robust motion prior, we introduce a second-stage camera-trajectory control module to compose human dynamics with viewpoint changes for coherent world exploration. We further construct a large-scale dataset with synchronized video, text, human-motion, and camera-trajectory annotations, organized into motion-centric and camera-centric subsets for decoupled training. Extensive experiments show stable long-horizon generation with precise controllability and high visual quality. See more at https://whydahuzi.github.io/Directing-the-World.github.io/.

Related papers

• UniMoCa: Unifying Motion and Camera Controls as Visual Proxies for Faithful Human Video Generation [50.391925716274926]
  textbfUniMoCa is a representation-driven framework that unifies motion and camera controls in visual space.<n>We show that UniMoCa achieves substantial gains in human motion control, camera control, temporal consistency, and camera-aware robustness with minimal additional complexity.
  arXiv  Detail & Related papers  (2026-08-03T09:18:13Z)
• Wonder: Video World Model Done Better [70.28870858365214]
  We present Wonder, a general-purpose video world model for real-time, camera-controllable world exploration.<n>Given an image or a conditional video, Wonder constructs a playable world where users can navigate interactively by moving the camera.<n>We introduce a novel camera conditioning with a dense coordinate field whose renderings provide spatially aligned motion and orientation cues.
  arXiv  Detail & Related papers  (2026-07-28T17:45:25Z)
• WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory [106.28234880163723]
  WorldDirector is a highly controllable video world model framework.<n>Our framework explicitly decouples semantic motion orchestration from visual generation.<n>We successfully preserve the exact visual identities of dynamic entities even when they re-enter the scene after prolonged periods out of view.
  arXiv  Detail & Related papers  (2026-07-02T17:59:59Z)
• DisCo: World Models with Discrete Camera Motion Control [79.86256515640231]
  We propose DisCo, a controllable video world model that conditions generation on a compact set of discrete action primitives to improve action separability.<n>DisCo achieves significantly more reliable action following while preserving visual quality.
  arXiv  Detail & Related papers  (2026-06-06T03:50:45Z)
• SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation [11.470401259593944]
  SymphoMotion is a unified motion-control framework that governs camera trajectories and object dynamics within a single model.<n>We show that SymphoMotion significantly outperforms existing methods in visual fidelity, camera controllability, and object-motion accuracy.
  arXiv  Detail & Related papers  (2026-04-04T12:59:24Z)
• DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning [82.28800081483224]
  We present DreamVideo- Omni, a unified framework enabling multisubject customization with omni-motion control.<n>To resolve multi-subject ambiguity, we introduce group and role embeddings to explicitly anchor motion signals to specific identities.<n>This provides motion-aware identity rewards in the latent space, prioritizing identity preservation aligned with human preferences.
  arXiv  Detail & Related papers  (2026-03-12T17:59:12Z)
• Hand2World: Autoregressive Egocentric Interaction Generation via Free-Space Hand Gestures [33.2764643227486]
  Egocentric interactive world models are essential for augmented reality and embodied AI, where visual generation must respond to user input with low latency, geometric consistency, and long-term stability.<n>We study egocentric interaction generation from a single scene image under free-space hand gestures, aiming to synthesize photorealistic videos in which hands enter the scene, interact with objects, and induce plausible world dynamics under head motion.<n>This setting introduces fundamental challenges, including distribution shift between free-space gestures and contact-heavy training data, ambiguity between hand motion and camera motion in monocular views, and the need for arbitrary-length video generation.
  arXiv  Detail & Related papers  (2026-02-10T09:51:07Z)
• Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation [73.73984727616198]
  We present Uni3C, a unified framework for precise control of both camera and human motion in video generation.<n>First, we propose a plug-and-play control module trained with a frozen video generative backbone, PCDController.<n>Second, we propose a jointly aligned 3D world guidance for the inference phase that seamlessly integrates both scenic point clouds and SMPL-X characters.
  arXiv  Detail & Related papers  (2025-04-21T07:10:41Z)
• TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation [7.900728371180723]
  We present TokenMotion, the first DiT-based video diffusion framework that enables fine-grained control over camera motion.<n>Our approach introduces a unified modeling framework utilizing a decouple-and-fuse strategy, bridged by a human-aware dynamic mask.<n>Our work represents a significant advancement in controllable video generation, with particular relevance for creative production applications.
  arXiv  Detail & Related papers  (2025-04-11T00:41:25Z)
• Image Conductor: Precision Control for Interactive Video Synthesis [90.2353794019393]
  Filmmaking and animation production often require sophisticated techniques for coordinating camera transitions and object movements. Image Conductor is a method for precise control of camera transitions and object movements to generate video assets from a single image.
  arXiv  Detail & Related papers  (2024-06-21T17:55:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.