论文标题
部分可观测时空混沌系统的无模型预测
INGeo: Accelerating Instant Neural Scene Reconstruction with Noisy Geometry Priors
论文作者
论文摘要
我们提出了一种加速3D场景和对象的重建的方法，旨在在边缘设备（例如移动电话和AR/VR耳机）上进行即时重建。尽管最近的作品已将现场重建训练加速到高端GPU上的微小/二级训练，但在Edge设备上即时培训的目标仍然存在很大的差距，而在Edge设备上的培训中，在许多新兴应用中（例如沉浸式AR/VR）仍然非常满意。为此，这项工作旨在通过利用目标场景的几何学先验来进一步加速培训。我们的方法提出了减轻不完善的几何学先验噪声的策略，以加速高度优化的即时NGP的训练速度。在NERF合成数据集上，我们的工作使用了一半的训练迭代，达到平均测试PSNR> 30。
We present a method that accelerates reconstruction of 3D scenes and objects, aiming to enable instant reconstruction on edge devices such as mobile phones and AR/VR headsets. While recent works have accelerated scene reconstruction training to minute/second-level on high-end GPUs, there is still a large gap to the goal of instant training on edge devices which is yet highly desired in many emerging applications such as immersive AR/VR. To this end, this work aims to further accelerate training by leveraging geometry priors of the target scene. Our method proposes strategies to alleviate the noise of the imperfect geometry priors to accelerate the training speed on top of the highly optimized Instant-NGP. On the NeRF Synthetic dataset, our work uses half of the training iterations to reach an average test PSNR of >30.
