Towards Consistent Long-Term Pose Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912499835600896 |
|---|---|
| author | Li, Yayuan Bellos, Filippos Corso, Jason |
| author_facet | Li, Yayuan Bellos, Filippos Corso, Jason |
| contents | Current approaches to pose generation rely heavily on intermediate representations, either through two-stage pipelines with quantization or autoregressive models that accumulate errors during inference. This fundamental limitation leads to degraded performance, particularly in long-term pose generation where maintaining temporal coherence is crucial. We propose a novel one-stage architecture that directly generates poses in continuous coordinate space from minimal context - a single RGB image and text description - while maintaining consistent distributions between training and inference. Our key innovation is eliminating the need for intermediate representations or token-based generation by operating directly on pose coordinates through a relative movement prediction mechanism that preserves spatial relationships, and a unified placeholder token approach that enables single-forward generation with identical behavior during training and inference. Through extensive experiments on Penn Action and First-Person Hand Action Benchmark (F-PHAB) datasets, we demonstrate that our approach significantly outperforms existing quantization-based and autoregressive methods, especially in long-term generation scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_18382 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Consistent Long-Term Pose Generation Li, Yayuan Bellos, Filippos Corso, Jason Computer Vision and Pattern Recognition Current approaches to pose generation rely heavily on intermediate representations, either through two-stage pipelines with quantization or autoregressive models that accumulate errors during inference. This fundamental limitation leads to degraded performance, particularly in long-term pose generation where maintaining temporal coherence is crucial. We propose a novel one-stage architecture that directly generates poses in continuous coordinate space from minimal context - a single RGB image and text description - while maintaining consistent distributions between training and inference. Our key innovation is eliminating the need for intermediate representations or token-based generation by operating directly on pose coordinates through a relative movement prediction mechanism that preserves spatial relationships, and a unified placeholder token approach that enables single-forward generation with identical behavior during training and inference. Through extensive experiments on Penn Action and First-Person Hand Action Benchmark (F-PHAB) datasets, we demonstrate that our approach significantly outperforms existing quantization-based and autoregressive methods, especially in long-term generation scenarios. |
| title | Towards Consistent Long-Term Pose Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.18382 |