Image-to-point-cloud (I2P) registration is a fundamental problem in computer vision, focusing on establishing 2D-3D correspondences between an image and a point cloud. The differential perspective-n-point (PnP) has been widely used to supervise I2P registration networks by enforcing the projective constraints on 2D-3D correspondences. However, differential PnP is highly sensitive to noise and outliers in the predicted correspondences. This issue hinders the effectiveness of correspondence learning. Inspired by the robustness of blind PnP against noise and outliers in correspondences, we propose an approximated blind PnP based correspondence learning approach. To mitigate the high computational cost of blind PnP, we simplify blind PnP to an amenable task of minimizing Chamfer distance between learned 2D and 3D keypoints, called MinCD-PnP. To effectively solve MinCD-PnP, we design a lightweight multi-task learning module, named as MinCD-Net, which can be easily integrated into the existing I2P registration architectures. Extensive experiments on 7-Scenes, RGBD-V2, ScanNet, and self-collected datasets demonstrate that MinCD-Net outperforms state-of-the-art methods and achieves a higher inlier ratio (IR) and registration recall (RR) in both cross-scene and cross-dataset settings.

Image-to-point cloud (I2P) registration is a fundamental task in computer vision, which aims to align pixels in 2D images with corresponding points in 3D point clouds. While deep learning based methods dominate this field, they often fail to generalize to the open domain. In this paper, we address open-domain I2P registration from the topology relationships perspective. Firstly, we find that topology relationships reflect sparse connections between pixels and points, which shows the significant potential in enhancing cross-modality feature interaction in the open domain. Building on this insight, we develop an I2P registration framework using topology relationships. After that, to construct and leverage the topology relationships between the heterogeneous 2D and 3D spaces, we design a registration network, Top-I2P, with correction-based topology reasoning and fast topology feature interaction modules. Extensive experiments on 7-Scenes, RGBD-V2, ScanNet, and self-collected I2P datasets demonstrate that Top-I2P achieves superior registration performance in open-domain scenarios.

As air pollution continues to pose a growing threat to human health and environmental well-being, accurate forecasting of pollutant concentration has become increasingly important. Existing prediction models can be divided into two categories: non-machine learning models and machine learning models. Nonmachine learning models excessively rely on historical data, while machine learning models have high time complexity and require large amounts of data. To solve the above problems, this paper proposes a spatial distance optimization-based model for predicting pollutant concentration. The proposed model uses a neural network for predicting pollutant concentration, with the nonlinear activation increasing the model's ability to fit nonlinear data. Additionally, it proposes a spatial distance optimization strategy that divides the surrounding monitoring stations based on their distance from the target station. As the neural network model deepens, the influence of more distant monitoring stations on the predicted values gradually reduces. The proposed model adapts the weights based on training errors, implicitly learning the distribution of the relationship between station distances and concentration values and fully exploiting the intrinsic information of the data. Simulation results show that the proposed model can achieve a prediction accuracy up to 6.38% higher than traditional methods.