发表机构
AIOZ; University of Liverpool; NTHU（AIOZ; 利物浦大学; 国立清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对人-场景交互中接触表示效率不足的问题，提出稀疏接触掩码与稀疏算子，在三个基准数据集的接触预测和场景合成任务上，实现至少12倍提速且精度优于现有最优模型。
AI 中文摘要
人-场景交互是一个活跃的研究课题，在虚拟现实、游戏、机器人和监控等领域有多项工业应用。尽管在网络架构方面已取得显著进展，这些进展可用于提升结果或优化模型参数以实现快速推理速度，但人体与其环境之间接触的高效表示仍然是一个开放的挑战。在本文中，我们提出了一种用于人-场景交互的新型高效人体接触表示。我们的主要贡献是引入了稀疏接触掩码，该掩码可策略性地选择必要的接触信息，大幅减少高维输入中的冗余数据。利用这种高效的接触表示，我们提出了一组稀疏算子，用于替换深度网络层内的传统密集算子以实现更快的计算。我们的方法不仅提高了计算速度，还过滤掉了非必要的接触数据，从而提升了人-场景交互模型的精度。为验证我们方法的有效性，我们在三个公共基准数据集上进行了密集实验，重点关注人-场景交互的两个关键任务：接触预测和场景合成。实验结果表明，我们的方法在重建准确性方面优于现有最优模型，且相较于近期基线模型实现了至少12倍的计算速度提升。
英文摘要
Human-scene interaction is an active research topic with several industrial applications in virtual reality, gaming, robotics, and surveillance. Despite significant progress in network architectures to improve the results or optimize models' parameters for fast inference speed, the efficient representation of contact between humans and their environments remains an open challenge. In this paper, we propose a new efficient human-contact representation for human-scene interaction. Our primary contribution is the introduction of sparse contact masks that strategically select essential contact information, significantly reducing redundant data in high-dimensional inputs. Leveraging this efficient contact representation, we propose a suite of sparse operators to replace traditional dense operators within deep network layers for faster computation. Our approach not only enhances computational speed but also filters out non-essential contact data, thereby improving the precision of human-scene interaction models. To validate the effectiveness of our method, we conduct intensive experiments across three public benchmark datasets, focusing on two critical tasks for human-scene interaction: contact prediction and scene synthesis. The experimental results show that our approach outperforms state-of-the-art models in reconstruction accuracy and achieves a computation speed-up of at least 12 times over recent baselines.
CommentsAccepted in ECCV 2026 Workshops
