神经场随机训练中的预条件器
Preconditioners for the Stochastic Training of Neural Fields
AI总结：
本文提出曲率感知对角预条件器以加速神经场随机训练，在图像重建、形状建模和NeRF任务中验证了有效性。
摘要：
神经场将连续多维信号编码为神经网络，从而在计算机视觉、机器人和几何学中实现多种应用。虽然Adam在随机优化中有效，但通常需要较长的训练时间。为解决此问题，我们探索替代优化技术以在不牺牲准确性的前提下加速训练。传统的二阶方法如L-BFGS不适用于随机设置。我们提出一个用于训练神经场的曲率感知对角预条件器的理论框架，并展示其在图像重建、形状建模和神经辐射场（NeRF）等任务中的有效性。
英文摘要：
Neural fields encode continuous multidimensional signals as neural networks, enabling diverse applications in computer vision, robotics, and geometry. While Adam is effective for stochastic optimization, it often requires long training times. To address this, we explore alternative optimization techniques to accelerate training without sacrificing accuracy. Traditional second-order methods like L-BFGS are unsuitable for stochastic settings. We propose a theoretical framework for training neural fields with curvature-aware diagonal preconditioners, demonstrating their effectiveness across tasks such as image reconstruction, shape modeling, and Neural Radiance Fields (NeRF).
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。
