|国家预印本平台
首页|Gen4D: Synthesizing Humans and Scenes in the Wild

Gen4D: Synthesizing Humans and Scenes in the Wild

Gen4D: Synthesizing Humans and Scenes in the Wild

来源:Arxiv_logoArxiv
英文摘要

Lack of input data for in-the-wild activities often results in low performance across various computer vision tasks. This challenge is particularly pronounced in uncommon human-centric domains like sports, where real-world data collection is complex and impractical. While synthetic datasets offer a promising alternative, existing approaches typically suffer from limited diversity in human appearance, motion, and scene composition due to their reliance on rigid asset libraries and hand-crafted rendering pipelines. To address this, we introduce Gen4D, a fully automated pipeline for generating diverse and photorealistic 4D human animations. Gen4D integrates expert-driven motion encoding, prompt-guided avatar generation using diffusion-based Gaussian splatting, and human-aware background synthesis to produce highly varied and lifelike human sequences. Based on Gen4D, we present SportPAL, a large-scale synthetic dataset spanning three sports: baseball, icehockey, and soccer. Together, Gen4D and SportPAL provide a scalable foundation for constructing synthetic datasets tailored to in-the-wild human-centric vision tasks, with no need for manual 3D modeling or scene design.

Jerrin Bright、Zhibo Wang、Yuhao Chen、Sirisha Rambhatla、John Zelek、David Clausi

计算技术、计算机技术体育

Jerrin Bright,Zhibo Wang,Yuhao Chen,Sirisha Rambhatla,John Zelek,David Clausi.Gen4D: Synthesizing Humans and Scenes in the Wild[EB/OL].(2025-06-03)[2025-06-18].https://arxiv.org/abs/2506.05397.点此复制

评论