Wonder: Video World Model Done Better

• URL: http://arxiv.org/abs/2607.26037v1
• Date: Tue, 28 Jul 2026 17:45:25 GMT
• Title: Wonder: Video World Model Done Better
• Abstract summary: 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.
• Score: 70.28870858365214
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Wonder, a general-purpose video world model for real-time, camera-controllable world exploration. Given an image or a conditional video, Wonder constructs a playable world where users can navigate interactively by moving the camera, discovering unseen regions, and revisiting previously observed areas in real time and over a long-term horizon. Achieving this capability requires a system-level co-design of control method, memory mechanism, and training strategy. We introduce a novel camera conditioning with a dense coordinate field whose renderings provide spatially aligned motion and orientation cues, allowing the model to interpret camera motion directly as visual evidence. To support fast and precise memory retrieval over a growing generation context, we propose an efficient sparse attention-based memory mechanism, enabling the model to selectively attend to a small set of relevant context tokens at inference time, regardless of actual context length. We further develop several techniques to rectify the self-forcing-style distillation pipeline, improving the student model's ability to respect control signals, as well as maintaining diverse generation modes and long-term memory from the teacher. Together, these components enable Wonder to synthesize diverse, minute-scale videos at 16 FPS while preserving coherent geometry, appearance, and dynamics across long rollouts. Beyond image-to-video generation, Wonder naturally supports video-conditioned generation, allowing existing dynamic scenes to be re-shot in real time.

Related papers

• Sekai2: From World Exploration to Interactive World Modeling [22.57939715452233]
  Sekai2 is a multi-source real-world video dataset that carries the world-exploration footage of Sekai toward interactive world modeling.<n>The release contains 128,892 clips totaling 2,826 hours from 10,428 source videos across 113 countries or regions.<n>Every clip includes a released camera trajectory and hierarchical annotations disentangling subject motion, environment dynamics, static scene content, and camera behavior, resulting in 649,597 temporally grounded segments.
  arXiv  Detail & Related papers  (2026-08-10T11:23:01Z)
• Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control [56.828569670698975]
  "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.
  arXiv  Detail & Related papers  (2026-06-26T11:08:09Z)
• OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation [42.159343032593014]
  We propose OmniRoam, a controllable panoramic video generation framework.<n>Our framework exploits the rich per-frame scene coverage and inherent long-term spatial and temporal consistency of panoramic representation.<n> Experiments show that our framework consistently outperforms state-of-the-art methods in terms of visual quality, controllability, and long-term scene consistency.
  arXiv  Detail & Related papers  (2026-03-31T17:59:33Z)
• Plenoptic Video Generation [80.3116444692858]
  We introduce PlenopticDreamer, a framework that synchronizes generative hallucinations to maintain synchronization-temporal memory.<n>The core idea is to train a multi-in-out video-conditioned model in an autoregressive manner.<n>Our training incorporates context-scaling to improve convergence, self-conditioning to hallucinations caused by error accumulation, and a long-video conditioning mechanism to support extended video generation.
  arXiv  Detail & Related papers  (2026-01-08T18:58:32Z)
• RELIC: Interactive Video World Model with Long-Horizon Memory [74.81433479334821]
  A truly interactive world model requires real-time long-horizon streaming, consistent spatial memory, and precise user control.<n>We present RELIC, a unified framework that tackles these three challenges altogether.<n>Given a single image and a text description, RELIC enables memory-aware, long-duration exploration of arbitrary scenes in real time.
  arXiv  Detail & Related papers  (2025-12-03T18:29:20Z)
• Video World Models with Long-term Spatial Memory [110.530715838396]
  We introduce a novel framework to enhance long-term consistency of video world models.<n>Our framework includes mechanisms to store and retrieve information from the long-term spatial memory.<n>Our evaluations show improved quality, consistency, and context length compared to relevant baselines.
  arXiv  Detail & Related papers  (2025-06-05T17:42:34Z)
• Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention [62.2447324481159]
  Cavia is a novel framework for camera-controllable, multi-view video generation. Our framework extends the spatial and temporal attention modules, improving both viewpoint and temporal consistency. Cavia is the first of its kind that allows the user to specify distinct camera motion while obtaining object motion.
  arXiv  Detail & Related papers  (2024-10-14T17:46:32Z)

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.