{"ID":2827396,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.16199","arxiv_id":"2512.16199","title":"Avatar4D: Synthesizing Domain-Specific 4D Humans for Real-World Pose Estimation","abstract":"We present Avatar4D, a real-world transferable pipeline for generating customizable synthetic human motion datasets tailored to domain-specific applications. Unlike prior works, which focus on general, everyday motions and offer limited flexibility, our approach provides fine-grained control over body pose, appearance, camera viewpoint, and environmental context, without requiring any manual annotations. To validate the impact of Avatar4D, we focus on sports, where domain-specific human actions and movement patterns pose unique challenges for motion understanding. In this setting, we introduce Syn2Sport, a large-scale synthetic dataset spanning sports, including baseball and ice hockey. Avatar4D features high-fidelity 4D (3D geometry over time) human motion sequences with varying player appearances rendered in diverse environments. We benchmark several state-of-the-art pose estimation models on Syn2Sport and demonstrate their effectiveness for supervised learning, zero-shot transfer to real-world data, and generalization across sports. Furthermore, we evaluate how closely the generated synthetic data aligns with real-world datasets in feature space. Our results highlight the potential of such systems to generate scalable, controllable, and transferable human datasets for diverse domain-specific tasks without relying on domain-specific real data.","short_abstract":"We present Avatar4D, a real-world transferable pipeline for generating customizable synthetic human motion datasets tailored to domain-specific applications. Unlike prior works, which focus on general, everyday motions and offer limited flexibility, our approach provides fine-grained control over body pose, appearance,...","url_abs":"https://arxiv.org/abs/2512.16199","url_pdf":"https://arxiv.org/pdf/2512.16199v1","authors":"[\"Jerrin Bright\",\"Zhibo Wang\",\"Dmytro Klepachevskyi\",\"Yuhao Chen\",\"Sirisha Rambhatla\",\"David Clausi\",\"John Zelek\"]","published":"2025-12-18T05:46:15Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}