Reliability-Regulated Trajectory Optimization for Progressive COLMAP-Free 3D Gaussian Splatting

📄 arXiv: 2609.30865v1 📥 PDF

作者: Zijian Wu, Jinliang Wang, Zidian Lin, Ying Song, Ziqian Lu, Hanjie Ma, Zhen Ye, Mingfeng Jiang

分类: cs.CV

发布日期: 2026-09-25

🔗 代码/项目: GITHUB

💡 一句话要点

提出可靠性调节的轨迹优化以解决COLMAP-free 3D Gaussian Splatting问题

🎯 匹配领域: 支柱一：机器人控制 (Robot Control) 支柱三：空间感知与语义 (Perception & Semantics)

关键词: 三维重建 相机姿态估计 轨迹优化 自监督学习 计算机视觉

📋 核心要点

  1. 现有的COLMAP-free 3DGS方法在逐步相机姿态跟踪中容易受到早期配对跟踪不准确的影响，导致误差累积。
  2. 本文提出了一种可靠性调节的轨迹优化框架，通过自监督机制调节相机轨迹估计，解决了逐步漂移问题。
  3. 在Tanks and Temples和CO3D-V2基准测试中，实验结果显示该方法显著提高了相机轨迹的准确性和新视角渲染质量。

📝 摘要（中文）

COLMAP-free 3D Gaussian Splatting（3DGS）避免了计算量大的结构光束法（SfM）流程，但逐步相机姿态跟踪仍然容易受到误差累积的影响。本文提出了一种统一的可靠性调节轨迹优化框架，通过自监督的双向循环一致性机制，系统性地调节逐步相机轨迹估计，显著提高了相机轨迹的准确性和新视角渲染质量。实验结果表明，该方法在Tanks and Temples和CO3D-V2基准上优于现有无姿态基线，代码已公开。

🔬 方法详解

问题定义：本文旨在解决COLMAP-free 3D Gaussian Splatting中逐步相机姿态跟踪的误差累积问题。现有方法在早期配对跟踪不准确时，会导致后续帧初始化的错误，影响场景表示的准确性。

核心思路：提出的框架通过引入可靠性信号，调节相机轨迹估计，分为前向运动传播和回顾轨迹修正两个阶段，旨在减少误差传播并提高整体跟踪精度。

技术框架：整体架构包括两个主要模块：前向运动传播模块和回顾轨迹修正模块。前者通过可靠性信号引导运动初始化，后者则在滑动窗口内动态加权相对姿态一致性约束。

关键创新：本研究的创新点在于引入了自监督的双向循环一致性机制，统一调节前向和回顾的轨迹估计，避免了对外部神经先验的依赖。

关键设计：在技术细节上，框架中使用的可靠性信号动态调整运动传播和轨迹修正的权重，确保了在不可信转变时的安全拦截。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，提出的方法在Tanks and Temples和CO3D-V2基准上，相机轨迹准确性和新视角渲染质量显著提高，超越了现有的无姿态基线，具体性能提升幅度未知。

🎯 应用场景

该研究的潜在应用领域包括计算机视觉、机器人导航和增强现实等。通过提高相机轨迹的准确性，能够在这些领域实现更高质量的三维重建和实时渲染，具有重要的实际价值和未来影响。

📄 摘要（原文）

COLMAP-free 3D Gaussian Splatting (3DGS) bypasses computationally expensive structure-from-motion (SfM) pipelines, yet progressive camera pose tracking remains fundamentally vulnerable to error compounding---early pairwise tracking inaccuracies both corrupt subsequent frame initializations and remain permanently frozen in the scene representation. Rather than relying on heavyweight external neural priors or treating progressive tracking through isolated heuristic fixes, we propose a unified reliability-regulated trajectory optimization framework for progressive COLMAP-free 3DGS. At its core, our framework establishes an intrinsic, self-supervised bidirectional cycle-consistency mechanism that systematically regulates progressive camera trajectory estimation across two complementary temporal horizons: (1) Forward Motion Propagation, where the online reliability signal adaptively gates first-order kinematic warm-starts of rigid motion into upcoming pairwise registrations, supplying informed directional search priors while safely intercepting untrusted transitions; and (2) Retrospective Trajectory Correction, where the same reliability signal dynamically weights relative-pose consistency constraints within a sliding window of neighboring camera poses. By governing both prospective state initialization and retrospective trajectory consolidation through a unified reliability regulator, our self-contained framework resolves progressive drift without external priors or offline preprocessing. Extensive evaluations on Tanks and Temples and CO3D-V2 benchmarks show that our method substantially improves camera trajectory accuracy and novel-view rendering quality, outperforming existing unposed baselines. Code is available at https://github.com/Zijian1026/RRTO-CF3DGS.