This research presents a novel depth estimation algorithm based on a
Transformer-encoder architecture, tailored for the NYU and KITTI Depth Dataset.
This research adopts a transformer model, initially renowned for its success in
natural language processing, to capture intricate spatial relationships in
visual data for depth estimation tasks. A significant innovation of the
research is the integration of a composite loss function that combines
Structural Similarity Index Measure (SSIM) with Mean Squared Error (MSE). This
combined loss function is designed to ensure the structural integrity of the
predicted depth maps relative to the original images (via SSIM) while
minimizing pixel-wise estimation errors (via MSE). This research approach
addresses the challenges of over-smoothing often seen in MSE-based losses and
enhances the model's ability to predict depth maps that are not only accurate
but also maintain structural coherence with the input images. Through rigorous
training and evaluation using the NYU Depth Dataset, the model demonstrates
superior performance, marking a significant advancement in single-image depth
estimation, particularly in complex indoor and traffic environments.

该研究提出了一种基于 Transformer 编码器架构的创新深度估计算法，针对 NYU 和 KITTI 深度数据集。该研究采用 Transformer 模型来捕捉图像数据中的复杂空间关系以用于深度估计任务，并集成了结构相似性指数 (SSIM) 和均方误差 (MSE) 的复合损失函数，以确保预测的深度图像在结构上保持一致并最小化像素级估计误差。经过严格训练和评估，模型在 NYU 深度数据集上展现出卓越性能，为单幅图像深度估计，尤其是在复杂室内和交通环境中，带来了显著的进展。

基于 Transformer 编码器和特征融合的深度估计算法

Depth Estimation Algorithm Based on Transformer-Encoder and Feature  Fusion

Depth maps contain geometric clues for assisting Salient Object Detection
(SOD). In this paper, we propose a novel Cross-Modal Weighting (CMW) strategy
to encourage comprehensive interactions between RGB and depth channels for
RGB-D SOD. Specifically, three RGB-depth interaction modules, named CMW-L,
CMW-M and CMW-H, are developed to deal with respectively low-, middle- and
high-level cross-modal information fusion. These modules use Depth-to-RGB
Weighing (DW) and RGB-to-RGB Weighting (RW) to allow rich cross-modal and
cross-scale interactions among feature layers generated by different network
blocks. To effectively train the proposed Cross-Modal Weighting Network
(CMWNet), we design a composite loss function that summarizes the errors
between intermediate predictions and ground truth over different scales. With
all these novel components working together, CMWNet effectively fuses
information from RGB and depth channels, and meanwhile explores object
localization and details across scales. Thorough evaluations demonstrate CMWNet
consistently outperforms 15 state-of-the-art RGB-D SOD methods on seven popular
benchmarks.

本研究提出一种跨模型加权策略（CMW），采用三个 RGB - 深度交互模块（CMW-L、CMW-M 和 CMW-H）来分别处理低、中、高级别跨模式融合信息，并使用深度到 RGB 加权（DW）和 RGB 到 RGB 加权（RW）来允许由不同网络块生成的特征层之间进行丰富的跨模式和跨尺度交互，有效地融合 RGB 和深度通道的信息，同时探索不同尺度的物体定位和细节，实验结果表明，该方法在七个常用基准测试中优于 15 种现有的 RGB-D SOD 方法。