SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance
This work addresses the need for generating human-like motions for applications in virtual and physical robotics, representing an incremental improvement in motion generation techniques.
The paper tackles the problem of generating realistic human motions in dynamic environments by introducing SemGeoMo, a method that uses semantic and geometric guidance to improve motion quality, achieving state-of-the-art performance on three datasets.
Generating reasonable and high-quality human interactive motions in a given dynamic environment is crucial for understanding, modeling, transferring, and applying human behaviors to both virtual and physical robots. In this paper, we introduce an effective method, SemGeoMo, for dynamic contextual human motion generation, which fully leverages the text-affordance-joint multi-level semantic and geometric guidance in the generation process, improving the semantic rationality and geometric correctness of generative motions. Our method achieves state-of-the-art performance on three datasets and demonstrates superior generalization capability for diverse interaction scenarios. The project page and code can be found at https://4dvlab.github.io/project_page/semgeomo/.