The rapid development of 3D acquisition technology has made it possible to
obtain point clouds of real-world terrains. However, due to limitations in
sensor acquisition technology or specific requirements, point clouds often
contain defects such as holes with missing data. Inpainting algorithms are
widely used to patch these holes. However, existing traditional inpainting
algorithms rely on precise hole boundaries, which limits their ability to
handle cases where the boundaries are not well-defined. On the other hand,
learning-based completion methods often prioritize reconstructing the entire
point cloud instead of solely focusing on hole filling. Based on the fact that
real-world terrain exhibits both global smoothness and rich local detail, we
propose a novel representation for terrain point clouds. This representation
can help to repair the holes without clear boundaries. Specifically, it
decomposes terrains into low-frequency and high-frequency components, which are
represented by B-spline surfaces and relative height maps respectively. In this
way, the terrain point cloud inpainting problem is transformed into a B-spline
surface fitting and 2D image inpainting problem. By solving the two problems,
the highly complex and irregular holes on the terrain point clouds can be
well-filled, which not only satisfies the global terrain undulation but also
exhibits rich geometric details. The experimental results also demonstrate the
effectiveness of our method.

利用 3D 采集技术对实际地形进行点云获取，然后通过 B 样条曲面对地形点云进行补洞修复，既满足全局地形起伏又展现丰富的几何细节。

基于信号分解的地形点云修复

Terrain Point Cloud Inpainting via Signal Decomposition

Hyperspectral images are typically composed of hundreds of narrow and
contiguous spectral bands, each containing information about the material
composition of the imaged scene. However, these images can be affected by
various sources of noise, distortions, or data losses, which can significantly
degrade their quality and usefulness. To address these problems, we introduce
two novel self-supervised Hyperspectral Images (HSI) inpainting algorithms: Low
Rank and Sparsity Constraint Plug-and-Play (LRS-PnP), and its extension
LRS-PnP-DIP, which features the strong learning capability, but is still free
of external training data. We conduct the stability analysis under some mild
assumptions which guarantees the algorithm to converge. It is specifically very
helpful for the practical applications. Extensive experiments demonstrate that
the proposed solution is able to produce visually and qualitatively superior
inpainting results, achieving state-of-the-art performance. The code for
reproducing the results is available at
https://github.com/shuoli0708/LRS-PnP-DIP.

本文介绍了两种新型的自我监督高光谱图像修复算法：低秩和稀疏约束插入并播放（LRS-PnP），以及其扩展 LRS-PnP-DIP，其具有强大的学习能力，但仍然不需要外部训练数据。该算法能够稳定地收敛，并具有实际应用价值。广泛的实验表明，所提出的解决方案能够产生视觉和定性上优于现有方法的图像修复结果。

基于稀疏性和低秩约束的自监督深度高光谱修复

Self-supervised Deep Hyperspectral Inpainting with the Sparsity and  Low-Rank Considerations

We present an interactive system enabling users to manipulate images to
explore the robustness and sensitivity of deep learning image classifiers.
Using modern web technologies to run in-browser inference, users can remove
image features using inpainting algorithms and obtain new classifications in
real time, which allows them to ask a variety of "what if" questions by
experimentally modifying images and seeing how the model reacts. Our system
allows users to compare and contrast what image regions humans and machine
learning models use for classification, revealing a wide range of surprising
results ranging from spectacular failures (e.g., a "water bottle" image becomes
a "concert" when removing a person) to impressive resilience (e.g., a "baseball
player" image remains correctly classified even without a glove or base). We
demonstrate our system at The 2018 Conference on Computer Vision and Pattern
Recognition (CVPR) for the audience to try it live. Our system is open-sourced
at this https URL A video demo is
available at this https URL

本文介绍了一个交互式系统，使用户能够操作图像，探索深度学习图像分类器的稳健性和灵敏度，用户可以使用图像修复算法删除图像特征并实时获得新的分类，从而通过实验性地修改图像并观察模型的反应，提出各种 “如果” 的问题。我们的系统允许用户比较和对比人类和机器学习模型用于分类的图像区域，揭示了一系列惊人的结果，从可观的失败（例如，“水瓶” 图像在去除一个人后变成了 “音乐会” ）到卓越的弹性（例如，“棒球选手” 图像即使没有手套或基座也能正确分类）。我们在 CVPR 会议上展示了我们的系统以供观众直播尝试，我们的系统在 https 网址上开源，视频演示可在此 https 网址上获得。