UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909556639006720 |
|---|---|
| author | Li, Yiheng Hou, Ruibing Chang, Hong Shan, Shiguang Chen, Xilin |
| author_facet | Li, Yiheng Hou, Ruibing Chang, Hong Shan, Shiguang Chen, Xilin |
| contents | Human pose plays a crucial role in the digital age. While recent works have achieved impressive progress in understanding and generating human poses, they often support only a single modality of control signals and operate in isolation, limiting their application in real-world scenarios. This paper presents UniPose, a framework employing Large Language Models (LLMs) to comprehend, generate, and edit human poses across various modalities, including images, text, and 3D SMPL poses. Specifically, we apply a pose tokenizer to convert 3D poses into discrete pose tokens, enabling seamless integration into the LLM within a unified vocabulary. To further enhance the fine-grained pose perception capabilities, we facilitate UniPose with a mixture of visual encoders, among them a pose-specific visual encoder. Benefiting from a unified learning strategy, UniPose effectively transfers knowledge across different pose-relevant tasks, adapts to unseen tasks, and exhibits extended capabilities. This work serves as the first attempt at building a general-purpose framework for pose comprehension, generation, and editing. Extensive experiments highlight UniPose's competitive and even superior performance across various pose-relevant tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_16781 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing Li, Yiheng Hou, Ruibing Chang, Hong Shan, Shiguang Chen, Xilin Computer Vision and Pattern Recognition Artificial Intelligence Human pose plays a crucial role in the digital age. While recent works have achieved impressive progress in understanding and generating human poses, they often support only a single modality of control signals and operate in isolation, limiting their application in real-world scenarios. This paper presents UniPose, a framework employing Large Language Models (LLMs) to comprehend, generate, and edit human poses across various modalities, including images, text, and 3D SMPL poses. Specifically, we apply a pose tokenizer to convert 3D poses into discrete pose tokens, enabling seamless integration into the LLM within a unified vocabulary. To further enhance the fine-grained pose perception capabilities, we facilitate UniPose with a mixture of visual encoders, among them a pose-specific visual encoder. Benefiting from a unified learning strategy, UniPose effectively transfers knowledge across different pose-relevant tasks, adapts to unseen tasks, and exhibits extended capabilities. This work serves as the first attempt at building a general-purpose framework for pose comprehension, generation, and editing. Extensive experiments highlight UniPose's competitive and even superior performance across various pose-relevant tasks. |
| title | UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2411.16781 |