arXiv:2507.18255cs.CV2025-07ICCV被引 46

实时处理长序列图像,实现高效3D场景重建

LONG3R: Long Sequence Streaming 3D Reconstruction

  • 采用循环记忆机制,逐帧更新3D场景表示
  • 在长序列上优于现有方法,推理速度保持实时
  • 适合需要持续重建的实时应用如自动驾驶

近期多视角场景重建进展显著,但现有方法在处理图像流时仍受限于耗时的离线优化或较短序列,难以应用于实时场景。本文提出LONG3R(LOng sequence streaming 3D Reconstruction),一种面向长序列流式多视角3D重建的新模型。该模型通过循环运行,结合新观测与记忆更新实现实时处理。我们引入记忆门控机制筛选相关记忆,并通过双源精炼解码器实现粗到细的交互。为有效捕捉长序列记忆,提出3D时空记忆,动态修剪冗余空间信息,并自适应调整场景分辨率。为提升长序列性能并保持训练效率,采用两阶段课程训练策略。实验表明,LONG3R在长序列上显著优于当前最佳流式方法,同时维持实时推理速度。

原文摘要 · Abstract (English)

Recent advancements in multi-view scene reconstruction have been significant, yet existing methods face limitations when processing streams of input images. These methods either rely on time-consuming offline optimization or are restricted to shorter sequences, hindering their applicability in real-time scenarios. In this work, we propose LONG3R (LOng sequence streaming 3D Reconstruction), a novel model designed for streaming multi-view 3D scene reconstruction over longer sequences. Our model achieves real-time processing by operating recurrently, maintaining and updating memory with each new observation. We first employ a memory gating mechanism to filter relevant memory, which, together with a new observation, is fed into a dual-source refined decoder for coarse-to-fine interaction. To effectively capture long-sequence memory, we propose a 3D spatio-temporal memory that dynamically prunes redundant spatial information while adaptively adjusting resolution along the scene. To enhance our model's performance on long sequences while maintaining training efficiency, we employ a two-stage curriculum training strategy, each stage targeting specific capabilities. Experiments demonstrate that LONG3R outperforms state-of-the-art streaming methods, particularly for longer sequences, while maintaining real-time inference speed. Project page: https://zgchen33.github.io/LONG3R/.

3D重建实时处理长序列流式建模

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。