@inproceedings{Zhao:DART:2024,
  title = {A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control},
  author = {Zhao, Kaifeng and Li, Gen and Tang, Siyu},
  year = {2024}
}

DART achieves high-quality and efficient ( > 300 frames per second ) motion generation conditioned on online streams of text prompts. Furthermore, by integrating latent space optimization and reinforcement learning-based controls, DART enables various motion generation applications with spatial constraints and goals, including motion in-between, waypoint goal reaching, and human-scene interaction generation.

@inproceedings{li2024egogen,
  title={EgoGen: An Egocentric Synthetic Data Generator},
  author={Li, Gen and Zhao, Kaifeng and Zhang, Siwei and Lyu, Xiaozhong and Dusmanu, Mihai and Zhang, Yan and Pollefeys, Marc and Tang, Siyu},
  booktitle={CVPR},
  year={2024}
}

EgoGen is new synthetic data generator that can produce accurate and rich ground-truth training data for egocentric perception tasks.

@inproceedings{Zhao:ICCV:2023,
  title = {Synthesizing Diverse Human Motions in 3D Indoor Scenes},
  author = {Zhao, Kaifeng and Zhang, Yan and Wang, Shaofei and Beeler, Thabo and Tang, Siyu},
  booktitle = {International conference on computer vision (ICCV)},
  year = {2023}
}

In this work, we propose a method to generate a sequence of natural human-scene interaction events in real-world complex scenes as illustrated in this figure. The human first walks to sit on a stool (yellow to red), then walk to another chair to sit down (red to magenta), and finally walk to and lie on the sofa (magenta to blue).

@inproceedings{Zhao:ECCV:2022,
  title = {Compositional Human-Scene Interaction Synthesis with Semantic Control},
  author = {Zhao, Kaifeng and Wang, Shaofei and Zhang, Yan and Beeler, Thabo and Tang, Siyu},
  booktitle = {European conference on computer vision (ECCV)},
  year = {2022}
}

We propose COINS, for COmpositional INteraction Synthesis with Semantic Control. Given a pair of action and object instance as the semantic specification, our method generates virtual humans naturally interacting with the scene objects.