分离图片 - 拍摄者与被拍摄者_neural spline fields for burst image fusion and la-CSDN博客

本文链接：https://blog.csdn.net/qq_48824303/article/details/136342084

Neural Spline Fields for Burst Image Fusion and Layer Separation

@article{chugunov2023neural,
  title={Neural Spline Fields for Burst Image Fusion and Layer Separation},
  author={Chugunov, Ilya and Shustin, David and Yan, Ruyu and Lei, Chenyang and Heide, Felix},
  journal={arXiv preprint arXiv:2312.14235},
  year={2023}
}

在这里插入图片描述

Each photo in an image burst can be considered a sam ple of a complex 3D scene: the product of parallax, diffuse and specular materials, scene motion, and illuminant variation.

图像突发中的照片可以被认为是一个复杂3D场景的样本:视差，漫射和高光材料，场景运动和光源变化的产物。

While decomposing all of these effects from a stack of misaligned images is a highly ill-conditioned task, the conventional align-and-merge burst pipeline takes the other extreme: blending them into a single image.

虽然从一堆不对齐的图像中分解所有这些效果是一个高度病态的任务，但传统的对齐和合并突发管道采取了另一个极端:将它们混合到单个图像中。

In this work, we propose a versatile intermediate representation: a twolayer alpha-composited image plus flow model constructed with neural spline fields — networks trained to map input coordinates to spline control points.

在这项工作中，我们提出了一个通用的中间表示:一个由神经样条场构建的双层alpha合成图像加流模型-训练网络将输入坐标映射到样条控制点。

Our method is able to, during test-time optimization, jointly fuse a burst image capture into one high-resolution reconstruction and decompose it into transmission and obstruction layers.

我们的方法能够在测试时间优化过程中，将一幅突发图像捕获合并为一幅高分辨率重建图像，并将其分解为透射层和阻挡层。

Then, by discarding the obstruction layer, we can perform a range oftasks including seeing through occlusions, reflection suppression, and shadow removal.

然后，通过丢弃障碍物层，我们可以执行一系列任务，包括透过遮挡，反射抑制和阴影去除。

Validated on complex synthetic and in-the-wild captures we find that, with no postprocessing steps or learned priors, our generalizable model is able to outperform existing dedicated single-image and multi-view obstruction removal approaches.

通过对复杂合成和野外捕获的验证，我们发现，在没有后处理步骤或学习先验的情况下，我们的可推广模型能够优于现有的专用单图像和多视图障碍物去除方法。

官网：

https://github.com/princeton-computational-imaging/NSF

论文：

https://arxiv.org/pdf/2312.14235.pdf

APP：

https://github.com/Ilya-Muromets/Pani

https://github.com/Ilya-Muromets/Pani/releases/tag/pani-apk-1.2

更多干货请关注特辣番茄炒鸡蛋公众号

在这里插入图片描述