WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910252566315008 |
|---|---|
| author | Gu, Bohai Wu, Taiyi Yuan, Yueyang Liu, Jian Lu, Xiaocheng Du, Dazhao Zhang, Jie Lai, Jinxiang Yang, Shuai Zhao, Xiaotong Zhao, Alan Guo, Song |
| author_facet | Gu, Bohai Wu, Taiyi Yuan, Yueyang Liu, Jian Lu, Xiaocheng Du, Dazhao Zhang, Jie Lai, Jinxiang Yang, Shuai Zhao, Xiaotong Zhao, Alan Guo, Song |
| contents | Recent video-based world models have made pixel-space environments interactive at the camera level: users can navigate viewpoints while the model generates coherent visual continuations. Yet their action spaces remain incomplete: users can move the camera, but cannot act on individual objects. Since real-world interaction is inherently object-centric, such models remain closer to passive scene observers than truly manipulable environments. We present WorldCraft, a framework that expands interactive video world models from camera navigation to object-level trajectory actions. Given a user click and a sketched path, WorldCraft generates future frames in which the selected object follows the prescribed trajectory while the camera continues to navigate the scene. WorldCraft achieves this through a trajectory-centric control pipeline: First, Normalized World Trajectory (NWT) represents user-drawn motion in a camera-invariant world coordinate system and dynamically re-projects it under the current camera pose, separating object motion from camera-induced screen-space displacement; Spatial-Pathway LoRA (SP-LoRA) then injects this world-space signal through the model's spatial-control pathway, adding object manipulation capability while preserving the pretrained camera controller; finally, Trajectory-Anchored State Persistence (TASP) treats the world trajectory as a persistent spatial state and refreshes autoregressive memory after trajectory-conditioned generation, allowing moved objects to reappear at their updated positions after leaving the camera view. Experiments show that WorldCraft enables accurate object control, preserves the video-based world model's camera fidelity under camera-only evaluation, and maintains object state across long autoregressive rollouts with off-camera excursions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25077 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models Gu, Bohai Wu, Taiyi Yuan, Yueyang Liu, Jian Lu, Xiaocheng Du, Dazhao Zhang, Jie Lai, Jinxiang Yang, Shuai Zhao, Xiaotong Zhao, Alan Guo, Song Computer Vision and Pattern Recognition Recent video-based world models have made pixel-space environments interactive at the camera level: users can navigate viewpoints while the model generates coherent visual continuations. Yet their action spaces remain incomplete: users can move the camera, but cannot act on individual objects. Since real-world interaction is inherently object-centric, such models remain closer to passive scene observers than truly manipulable environments. We present WorldCraft, a framework that expands interactive video world models from camera navigation to object-level trajectory actions. Given a user click and a sketched path, WorldCraft generates future frames in which the selected object follows the prescribed trajectory while the camera continues to navigate the scene. WorldCraft achieves this through a trajectory-centric control pipeline: First, Normalized World Trajectory (NWT) represents user-drawn motion in a camera-invariant world coordinate system and dynamically re-projects it under the current camera pose, separating object motion from camera-induced screen-space displacement; Spatial-Pathway LoRA (SP-LoRA) then injects this world-space signal through the model's spatial-control pathway, adding object manipulation capability while preserving the pretrained camera controller; finally, Trajectory-Anchored State Persistence (TASP) treats the world trajectory as a persistent spatial state and refreshes autoregressive memory after trajectory-conditioned generation, allowing moved objects to reappear at their updated positions after leaving the camera view. Experiments show that WorldCraft enables accurate object control, preserves the video-based world model's camera fidelity under camera-only evaluation, and maintains object state across long autoregressive rollouts with off-camera excursions. |
| title | WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.25077 |