同时优化声学3D重建与漂移的传感器位姿，提升重建精度。
Acoustic Neural 3D Reconstruction Under Pose Drift
- 将6自由度位姿设为可学习参数，联合优化场景表示与位姿
- 在真实与仿真数据上实现显著位姿漂移下的高保真重建
- 适合做声学3D建模且传感器易漂移的场景应用
本文研究在传感器位姿漂移条件下，利用声学图像优化神经隐式表面的3D重建问题。当前最先进的3D声学建模算法高度依赖精确的位姿估计；传感器位姿的微小误差会导致严重的重建伪影。为此，本文提出一种联合优化神经场景表示与声纳位姿的算法。通过将6自由度（6DoF）位姿参数化为可学习变量，并对神经渲染器和隐式表示进行反向传播梯度更新，实现端到端优化。我们在真实与模拟数据集上验证了该方法，结果表明，即使在显著位姿漂移下，也能生成高质量的3D重建结果。
原文摘要 · Abstract (English)
We consider the problem of optimizing neural implicit surfaces for 3D reconstruction using acoustic images collected with drifting sensor poses. The accuracy of current state-of-the-art 3D acoustic modeling algorithms is highly dependent on accurate pose estimation; small errors in sensor pose can lead to severe reconstruction artifacts. In this paper, we propose an algorithm that jointly optimizes the neural scene representation and sonar poses. Our algorithm does so by parameterizing the 6DoF poses as learnable parameters and backpropagating gradients through the neural renderer and implicit representation. We validated our algorithm on both real and simulated datasets. It produces high-fidelity 3D reconstructions even under significant pose drift.
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。