6D pose estimation in space poses unique challenges that are not commonly
encountered in the terrestrial setting. One of the most striking differences is
the lack of atmospheric scattering, allowing objects to be visible from a great
distance while complicating illumination conditions. Currently available
benchmark datasets do not place a sufficient emphasis on this aspect and mostly
depict the target in close proximity.
Prior work tackling pose estimation under large scale variations relies on a
two-stage approach to first estimate scale, followed by pose estimation on a
resized image patch. We instead propose a single-stage hierarchical end-to-end
trainable network that is more robust to scale variations. We demonstrate that
it outperforms existing approaches not only on images synthesized to resemble
images taken in space but also on standard benchmarks.

本论文提出了一种单阶段的分层端对端可训练网络，可以更好地解决大规模空间场景中的 6D 姿态估计问题，相比现有方法在合成的太空图像和标准数据集上表现更优秀。关键词包括 6D 姿态估计、空间、大气散射、基准数据集和端对端可训练网络

空间中的宽度 - 深度范围 6D 物体姿态估计

Wide-Depth-Range 6D Object Pose Estimation in Space

In this paper, we present an end-to-end network, called Cycle-Dehaze, for
single image dehazing problem, which does not require pairs of hazy and
corresponding ground truth images for training. That is, we train the network
by feeding clean and hazy images in an unpaired manner. Moreover, the proposed
approach does not rely on estimation of the atmospheric scattering model
parameters. Our method enhances CycleGAN formulation by combining
cycle-consistency and perceptual losses in order to improve the quality of
textural information recovery and generate visually better haze-free images.
Typically, deep learning models for dehazing take low resolution images as
input and produce low resolution outputs. However, in the NTIRE 2018 challenge
on single image dehazing, high resolution images were provided. Therefore, we
apply bicubic downscaling. After obtaining low-resolution outputs from the
network, we utilize the Laplacian pyramid to upscale the output images to the
original resolution. We conduct experiments on NYU-Depth, I-HAZE, and O-HAZE
datasets. Extensive experiments demonstrate that the proposed approach improves
CycleGAN method both quantitatively and qualitatively.

本文提出了一种称为 Cycle-Dehaze 的端到端网络，用于单图像去雾问题，无需对成对的模糊和对应的真实图像进行训练，此方法不依赖于大气散射模型参数的估计。网络利用循环一致性和知觉损失增强 CycleGAN 的公式，以提高对纹理信息的恢复质量并生成更好的无雾图像。实验证明，该方法在 NYU-Depth、I-HAZE 和 O-HAZE 数据集上都能明显提高 CycleGAN 方法的质量。