Xuyang Tan

Existing guided depth map super-resolution methods have achieved promising results, but most of these methods suffer from large model parameters and high computational complexity, limiting their practical applicability. To address these challenges, this paper proposes a lightweight guided depth map super-resolution framework based on the Multi-Modal Attention Fusion Network (MAFNet). Specifically, we design a two-branch architecture for MAFNet, wherein the Swin branch captures global dependencies and the CNN branch extracts detailed local features, thus ensuring efficient processing. Furthermore, we propose a triple cross-modal attention module for effective fusion of color and depth information, and a compression selectivity bottleneck module to selectively filter essential features. Experimental evaluation on multiple public datasets demonstrates that the proposed MAFNet achieves a compelling balance between model performance and computational efficiency, offering a robust solution for guided depth map super-resolution.

Manual annotation for crowd counting remains labor-intensive and costly. Although existing semi-supervised methods partially alleviate this burden, they still face significant challenges regarding the quality of generated pseudo-labels and the utilization of unlabeled data. To address these issues, we propose a novel semi-supervised crowd counting framework, called Point-Adaptive Teacher (PAT). This framework integrates Adaptive Soft Threshold (AST) and contrastive learning to enhance pseudo-label quality and effectively leverage unlabeled data. Specifically, we employ the Swin Transformer as the backbone and develop Swin-P2PNet, which captures global contextual information through hierarchical window attention, improving the accuracy of pseudo-labels. Additionally, we design the AST that dynamically adjusts the sample loss weight by combining confidence and uncertainty predictions, thereby alleviating the effect of noise in pseudo-labels. Finally, we introduce a contrastive learning strategy requiring no extra parameters. This strategy enhances the model’s ability to learn latent representations from unlabeled data. Extensive experiments have been conducted on three public datasets, namely ShanghaiTech, JHU-Crowd++, and UCF-QNRF. The results demonstrate that our method achieves performance comparable to state-of-the-art methods.

Guided depth super-resolution (GDSR) aims to enhance the level of detail in low-resolution depth images by utilizing the information present in the corresponding high-resolution RGB images. While existing methods utilize different approaches to guide the RGB image to the source image, they often ignore the texture similarity between these two images and usually suffer from unsatisfactory outline reconstruction of the depth map. In this article, we introduce an adaptive texture migration network (ATMNet) designed to mine rich feature information from RGB images and migrate them to the depth image. Specifically, we propose a multi-modal feature extractor (MMFE) to extract private and shared features between the depth map and RGB image. In addition, we present a texture migration module (TMM) to remap and fuse the features extracted from the raw image pairs. Last but not least, we develop a weighted adaptive loss to enhance the reconstruction of the edge areas in the depth map. Extensive experiments on public datasets such as Middlebury, NYUv2, and DIML demonstrate that our method outperforms the existing state-of-the-art GDSR methods and strikes a remarkable balance between performance and efficiency. The source code is available at https://github.com/MuggleTan/ATMNet .