SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914620383428608 |
|---|---|
| author | He, Ziheng Chen, Yixiang Yang, Ning Wu, Zhanqian Ma, Qisen Xu, Yuan Yang, Jiabing Li, Peiyan Wu, Xiangnan Wang, Xiaofeng Zhu, Zheng Liu, Jing Liu, Nianfeng Huang, Yan |
| author_facet | He, Ziheng Chen, Yixiang Yang, Ning Wu, Zhanqian Ma, Qisen Xu, Yuan Yang, Jiabing Li, Peiyan Wu, Xiangnan Wang, Xiaofeng Zhu, Zheng Liu, Jing Liu, Nianfeng Huang, Yan |
| contents | Embodied world models have emerged as a promising paradigm in robotics by predicting how robot actions affect the surrounding scene. However, the rollout inference remains computationally expensive in pixel space, as long-horizon manipulation videos typically have to be generated frame by frame. This cost cannot be easily reduced by indiscriminately dropping frames, since downstream policies rely on complete preservation of sparse task-relevant events such as approach, contact, grasp, and release. To address this challenge, we propose Sparse Keyframe Interpolation Paradigm (SKIP), an event-preserving sparse-to-dense framework that avoids dense frame-by-frame generation. SKIP first identifies task-relevant keyframes by leveraging robot-aware multimodal features. It then synthesizes only these keyframes with a sparse video diffusion model. A learned gap predictor and an action-conditioned interpolator subsequently reconstruct the missing intervals according to the robot actions. On LIBERO, SKIP generates dense rollouts $4.16\times$ faster than a dense baseline while improving visual fidelity and reducing aggregate FVD by $89.0\%$. Importantly, SKIP-generated videos are effective policy-training data. Even when they fully replace real demonstrations, $π_{0.5}$ success drops only $1.3$ pp in LIBERO simulation and $6.7$ pp on the real robot, whereas fully dense frame-by-frame generation collapses by $48$ to $58$ pp. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_00664 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models He, Ziheng Chen, Yixiang Yang, Ning Wu, Zhanqian Ma, Qisen Xu, Yuan Yang, Jiabing Li, Peiyan Wu, Xiangnan Wang, Xiaofeng Zhu, Zheng Liu, Jing Liu, Nianfeng Huang, Yan Robotics Computer Vision and Pattern Recognition Embodied world models have emerged as a promising paradigm in robotics by predicting how robot actions affect the surrounding scene. However, the rollout inference remains computationally expensive in pixel space, as long-horizon manipulation videos typically have to be generated frame by frame. This cost cannot be easily reduced by indiscriminately dropping frames, since downstream policies rely on complete preservation of sparse task-relevant events such as approach, contact, grasp, and release. To address this challenge, we propose Sparse Keyframe Interpolation Paradigm (SKIP), an event-preserving sparse-to-dense framework that avoids dense frame-by-frame generation. SKIP first identifies task-relevant keyframes by leveraging robot-aware multimodal features. It then synthesizes only these keyframes with a sparse video diffusion model. A learned gap predictor and an action-conditioned interpolator subsequently reconstruct the missing intervals according to the robot actions. On LIBERO, SKIP generates dense rollouts $4.16\times$ faster than a dense baseline while improving visual fidelity and reducing aggregate FVD by $89.0\%$. Importantly, SKIP-generated videos are effective policy-training data. Even when they fully replace real demonstrations, $π_{0.5}$ success drops only $1.3$ pp in LIBERO simulation and $6.7$ pp on the real robot, whereas fully dense frame-by-frame generation collapses by $48$ to $58$ pp. |
| title | SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2606.00664 |