The Attention Restoration Theory (ART) presents a theoretical framework with
four essential indicators (being away, extent, fascinating, and compatibility)
for comprehending urban and natural restoration quality. However, previous
studies relied on non-sequential data and non-spatial dependent methods, which
overlooks the impact of spatial structure defined here as the positional
relationships between scene entities on restoration quality. The past methods
also make it challenging to measure restoration quality on an urban scale. In
this work, a spatial-dependent graph neural networks (GNNs) approach is
proposed to reveal the relation between spatial structure and restoration
quality on an urban scale. Specifically, we constructed two different types of
graphs at the street and city levels. The street-level graphs, using sequential
street view images (SVIs) of road segments to capture position relationships
between entities, were used to represent spatial structure. The city-level
graph, modeling the topological relationships of roads as non-Euclidean data
structures and embedding urban features (including Perception-features,
Spatial-features, and Socioeconomic-features), was used to measure restoration
quality. The results demonstrate that: 1) spatial-dependent GNNs model
outperforms traditional methods (Acc = 0.735, F1 = 0.732); 2) spatial structure
portrayed through sequential SVIs data significantly influences restoration
quality; 3) spaces with the same restoration quality exhibited distinct spatial
structures patterns. This study clarifies the association between spatial
structure and restoration quality, providing a new perspective to improve urban
well-being in the future.

利用空间相关的图神经网络 (GNNs) 方法构建了视角不同的两种图来研究城市尺度上的空间结构和恢复质量的关系，结果表明：1) 空间相关的 GNNs 模型优于传统方法；2) 通过顺序街景图像 (SVIs) 数据揭示了空间结构对恢复质量的显著影响；3) 恢复质量相同的空间展现了不同的空间结构模式。该研究阐明了空间结构与恢复质量之间的关联，为未来改善城市幸福感提供了新的视角。

空间结构如何影响心理恢复？一种基于图神经网络和街景图像的方法

How does spatial structure affect psychological restoration? A method  based on Graph Neural Networks and Street View Imagery

Based on the variational framework of the image denoising problem, we
introduce a novel image denoising regularizer that combines anisotropic total
variation model (ATV) and structure tensor total variation model (STV) in this
paper. The model can effectively capture the first-order information of the
image and maintain local features during the denoising process by applying the
matrix weighting operator proposed in the ATV model to the patch-based Jacobian
matrix in the STV model. Denoising experiments on grayscale and RGB color
images demonstrate that the suggested model can produce better restoration
quality in comparison to other well-known methods based on
total-variation-based models and the STV model.

本文提出了一种新的图像去噪正则化模型，结合了各向异性全变差模型和结构张量全变差模型，通过应用 ATV 模型中的矩阵加权算子到 STV 模型中的基于块的 Jacobian 矩阵，能够更好地维护本地特征，比其他基于全变差模型和 STV 模型的知名方法产生更好的恢复质量。

加权结构张量全变差用于图像去噪

Weighted structure tensor total variation for image denoising

The goal of image restoration (IR), a fundamental issue in computer vision,
is to restore a high-quality (HQ) image from its degraded low-quality (LQ)
observation. Multiple HQ solutions may correspond to an LQ input in this poorly
posed problem, creating an ambiguous solution space. This motivates the
investigation and incorporation of prior knowledge in order to effectively
constrain the solution space and enhance the quality of the restored images. In
spite of the pervasive use of hand-crafted and learned priors in IR, limited
attention has been paid to the incorporation of knowledge from large-scale
foundation models. In this paper, we for the first time leverage the prior
knowledge of the state-of-the-art segment anything model (SAM) to boost the
performance of existing IR networks in an parameter-efficient tuning manner. In
particular, the choice of SAM is based on its robustness to image degradations,
such that HQ semantic masks can be extracted from it. In order to leverage
semantic priors and enhance restoration quality, we propose a lightweight SAM
prior tuning (SPT) unit. This plug-and-play component allows us to effectively
integrate semantic priors into existing IR networks, resulting in significant
improvements in restoration quality. As the only trainable module in our
method, the SPT unit has the potential to improve both efficiency and
scalability. We demonstrate the effectiveness of the proposed method in
enhancing a variety of methods across multiple tasks, such as image
super-resolution and color image denoising.

该研究论文利用新型的图像分割神经网络，提出一种轻量级的先验调整单元，将先验知识融入现有的 IR 网络，提高了图像还原的质量。

图像恢复中 SAM 先验探究

A Dive into SAM Prior in Image Restoration

Super-Resolution (SR) is a fundamental computer vision task that aims to
obtain a high-resolution clean image from the given low-resolution counterpart.
This paper reviews the NTIRE 2021 Challenge on Video Super-Resolution. We
present evaluation results from two competition tracks as well as the proposed
solutions. Track 1 aims to develop conventional video SR methods focusing on
the restoration quality. Track 2 assumes a more challenging environment with
lower frame rates, casting spatio-temporal SR problem. In each competition, 247
and 223 participants have registered, respectively. During the final testing
phase, 14 teams competed in each track to achieve state-of-the-art performance
on video SR tasks.

本论文回顾了 NTIRE 2021 年的超分辨率视频挑战赛，共 247 个和 223 个参赛者参加了赛事，14 个团队在每个赛道上竞争，以在视频 SR 任务中实现最先进的表现。主要关键词有超分辨率，计算机视觉，视频，NTIRE 2021 年挑战赛和恢复质量。