论文标题
Alignerf：通过对齐感知训练的高保真神经辐射场
AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training
论文作者
论文摘要
神经辐射场（NERFS）是将3D场景建模为连续函数的强大表示。尽管Nerf能够以观看依赖性效果渲染复杂的3D场景，但很少有努力在高分辨率环境中探索其极限。具体而言，现有的基于NERF的方法在重建高分辨率真实场景时面临几个限制，包括大量参数，未对准的输入数据和过度流畅的详细信息。在这项工作中，我们对使用高分辨率数据进行了第一项有关培训NERF的试点研究，并提出了相应的解决方案：1）将多层感知器（MLP）与卷积层结合，可以编码更多的邻域信息，同时减少参数总数； 2）一种新型的培训策略，以解决由移动物体或小型摄像机校准错误引起的未对准； 3）高频意识损失。我们的方法几乎是免费的，而没有引入明显的培训/测试成本，而不同数据集的实验表明，与当前最新的NERF模型相比，它可以恢复更多高频细节。项目页面：\ url {https://yifanjiang.net/alignerf。}
Neural Radiance Fields (NeRFs) are a powerful representation for modeling a 3D scene as a continuous function. Though NeRF is able to render complex 3D scenes with view-dependent effects, few efforts have been devoted to exploring its limits in a high-resolution setting. Specifically, existing NeRF-based methods face several limitations when reconstructing high-resolution real scenes, including a very large number of parameters, misaligned input data, and overly smooth details. In this work, we conduct the first pilot study on training NeRF with high-resolution data and propose the corresponding solutions: 1) marrying the multilayer perceptron (MLP) with convolutional layers which can encode more neighborhood information while reducing the total number of parameters; 2) a novel training strategy to address misalignment caused by moving objects or small camera calibration errors; and 3) a high-frequency aware loss. Our approach is nearly free without introducing obvious training/testing costs, while experiments on different datasets demonstrate that it can recover more high-frequency details compared with the current state-of-the-art NeRF models. Project page: \url{https://yifanjiang.net/alignerf.}
