Autonomous Character-Scene Interaction Synthesis from Text Instruction
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_ | 1866913537255800832 |
|---|---|
| author | Jiang, Nan He, Zimo Wang, Zi Li, Hongjie Chen, Yixin Huang, Siyuan Zhu, Yixin |
| author_facet | Jiang, Nan He, Zimo Wang, Zi Li, Hongjie Chen, Yixin Huang, Siyuan Zhu, Yixin |
| contents | Synthesizing human motions in 3D environments, particularly those with complex activities such as locomotion, hand-reaching, and human-object interaction, presents substantial demands for user-defined waypoints and stage transitions. These requirements pose challenges for current models, leading to a notable gap in automating the animation of characters from simple human inputs. This paper addresses this challenge by introducing a comprehensive framework for synthesizing multi-stage scene-aware interaction motions directly from a single text instruction and goal location. Our approach employs an auto-regressive diffusion model to synthesize the next motion segment, along with an autonomous scheduler predicting the transition for each action stage. To ensure that the synthesized motions are seamlessly integrated within the environment, we propose a scene representation that considers the local perception both at the start and the goal location. We further enhance the coherence of the generated motion by integrating frame embeddings with language input. Additionally, to support model training, we present a comprehensive motion-captured dataset comprising 16 hours of motion sequences in 120 indoor scenes covering 40 types of motions, each annotated with precise language descriptions. Experimental results demonstrate the efficacy of our method in generating high-quality, multi-stage motions closely aligned with environmental and textual conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03187 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Autonomous Character-Scene Interaction Synthesis from Text Instruction Jiang, Nan He, Zimo Wang, Zi Li, Hongjie Chen, Yixin Huang, Siyuan Zhu, Yixin Computer Vision and Pattern Recognition Synthesizing human motions in 3D environments, particularly those with complex activities such as locomotion, hand-reaching, and human-object interaction, presents substantial demands for user-defined waypoints and stage transitions. These requirements pose challenges for current models, leading to a notable gap in automating the animation of characters from simple human inputs. This paper addresses this challenge by introducing a comprehensive framework for synthesizing multi-stage scene-aware interaction motions directly from a single text instruction and goal location. Our approach employs an auto-regressive diffusion model to synthesize the next motion segment, along with an autonomous scheduler predicting the transition for each action stage. To ensure that the synthesized motions are seamlessly integrated within the environment, we propose a scene representation that considers the local perception both at the start and the goal location. We further enhance the coherence of the generated motion by integrating frame embeddings with language input. Additionally, to support model training, we present a comprehensive motion-captured dataset comprising 16 hours of motion sequences in 120 indoor scenes covering 40 types of motions, each annotated with precise language descriptions. Experimental results demonstrate the efficacy of our method in generating high-quality, multi-stage motions closely aligned with environmental and textual conditions. |
| title | Autonomous Character-Scene Interaction Synthesis from Text Instruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.03187 |