Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.03334 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911208065466368 |
|---|---|
| author | Xiang, Xunzhi Chen, Yabo Zhang, Guiyu Wang, Zhongyu Gao, Zhe Xiang, Quanming Shang, Gonghu Liu, Junqi Huang, Haibin Gao, Yang Zhang, Chi Fan, Qi Li, Xuelong |
| author_facet | Xiang, Xunzhi Chen, Yabo Zhang, Guiyu Wang, Zhongyu Gao, Zhe Xiang, Quanming Shang, Gonghu Liu, Junqi Huang, Haibin Gao, Yang Zhang, Chi Fan, Qi Li, Xuelong |
| contents | Current autoregressive diffusion models excel at video generation but are generally limited to short temporal durations. Our theoretical analysis indicates that the autoregressive modeling typically suffers from temporal drift caused by error accumulation and hinders parallelization in long video synthesis. To address these limitations, we propose a novel planning-then-populating framework centered on Macro-from-Micro Planning (MMPL) for long video generation. MMPL sketches a global storyline for the entire video through two hierarchical stages: Micro Planning and Macro Planning. Specifically, Micro Planning predicts a sparse set of future keyframes within each short video segment, offering motion and appearance priors to guide high-quality video segment generation. Macro Planning extends the in-segment keyframes planning across the entire video through an autoregressive chain of micro plans, ensuring long-term consistency across video segments. Subsequently, MMPL-based Content Populating generates all intermediate frames in parallel across segments, enabling efficient parallelization of autoregressive generation. The parallelization is further optimized by Adaptive Workload Scheduling for balanced GPU execution and accelerated autoregressive video generation. Extensive experiments confirm that our method outperforms existing long video generation models in quality and stability. Generated videos and comparison results are in our project page. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03334 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation Xiang, Xunzhi Chen, Yabo Zhang, Guiyu Wang, Zhongyu Gao, Zhe Xiang, Quanming Shang, Gonghu Liu, Junqi Huang, Haibin Gao, Yang Zhang, Chi Fan, Qi Li, Xuelong Computer Vision and Pattern Recognition Current autoregressive diffusion models excel at video generation but are generally limited to short temporal durations. Our theoretical analysis indicates that the autoregressive modeling typically suffers from temporal drift caused by error accumulation and hinders parallelization in long video synthesis. To address these limitations, we propose a novel planning-then-populating framework centered on Macro-from-Micro Planning (MMPL) for long video generation. MMPL sketches a global storyline for the entire video through two hierarchical stages: Micro Planning and Macro Planning. Specifically, Micro Planning predicts a sparse set of future keyframes within each short video segment, offering motion and appearance priors to guide high-quality video segment generation. Macro Planning extends the in-segment keyframes planning across the entire video through an autoregressive chain of micro plans, ensuring long-term consistency across video segments. Subsequently, MMPL-based Content Populating generates all intermediate frames in parallel across segments, enabling efficient parallelization of autoregressive generation. The parallelization is further optimized by Adaptive Workload Scheduling for balanced GPU execution and accelerated autoregressive video generation. Extensive experiments confirm that our method outperforms existing long video generation models in quality and stability. Generated videos and comparison results are in our project page. |
| title | Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.03334 |