arXiv 2506.095182025-10-29cs.CV

HAIF-GS：面向动态场景的分层诱导流引导高斯泼溅

HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene

Institute of Computing Technology, Chinese Academy of Sciences, ICT（中国科学院计算技术研究所）；University of Chinese Academy of Sciences, UCAS（中国科学院大学）；The University of Queensland（昆士兰大学）；Jiangsu University（江苏大学）

Jianing Chen, Zehao Li, Yujun Cai, Hao Jiang, Chengxuan Qian, Juyuan Kang, Shuqin Gao, Honglong Zhao, Tianlu Mao, Yucheng Zhang

备注：: Accepted to NeurIPS 2025. Project page: https://echopickle.github.io/HAIF-GS.github.io/

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对动态3D场景重建中现有3DGS方法的三大局限，提出HAIF-GS框架，通过稀疏锚点驱动形变、自监督诱导流引导及分层锚点传播，在渲染质量、时间连贯性和效率上均优于现有方法。

摘要：

从单目视频重建动态3D场景仍是3D视觉领域的一项基础挑战。尽管3D高斯泼溅（3D Gaussian Splatting, 3DGS）在静态场景中实现了实时渲染，但由于难以学习结构化且时间一致的运动表示，将其扩展到动态场景颇具难度。这一挑战通常体现为现有方法的三个局限：高斯更新冗余、运动监督不足、复杂非刚性形变建模能力薄弱，这些问题共同阻碍了连贯且高效的动态重建。为解决上述局限，我们提出HAIF-GS统一框架，通过稀疏锚点驱动的形变实现结构化、一致的动态建模。该框架首先通过锚点滤波器识别运动相关区域，抑制静态区域的冗余更新；自监督诱导流引导形变模块利用多帧特征聚合推导锚点运动，无需显式光流标签；为进一步处理细粒度形变，分层锚点传播机制根据运动复杂度提升锚点分辨率并传播多层变换。在合成与真实基准上的大量实验验证，HAIF-GS在渲染质量、时间连贯性和重建效率上均显著优于现有动态3DGS方法。

英文摘要：

Reconstructing dynamic 3D scenes from monocular videos remains a fundamental challenge in 3D vision. While 3D Gaussian Splatting (3DGS) achieves real-time rendering in static settings, extending it to dynamic scenes is challenging due to the difficulty of learning structured and temporally consistent motion representations. This challenge often manifests as three limitations in existing methods: redundant Gaussian updates, insufficient motion supervision, and weak modeling of complex non-rigid deformations. These issues collectively hinder coherent and efficient dynamic reconstruction. To address these limitations, we propose HAIF-GS, a unified framework that enables structured and consistent dynamic modeling through sparse anchor-driven deformation. It first identifies motion-relevant regions via an Anchor Filter to suppress redundant updates in static areas. A self-supervised Induced Flow-Guided Deformation module induces anchor motion using multi-frame feature aggregation, eliminating the need for explicit flow labels. To further handle fine-grained deformations, a Hierarchical Anchor Propagation mechanism increases anchor resolution based on motion complexity and propagates multi-level transformations. Extensive experiments on synthetic and real-world benchmarks validate that HAIF-GS significantly outperforms prior dynamic 3DGS methods in rendering quality, temporal coherence, and reconstruction efficiency.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。