Inverse Stereo Matching Supervised Dense Point Cloud Reconstruction for Scenes
Ze Zong, Jie Xie, Jin Zhang, Cheng Wu · 2024
The reconstruction of dense point clouds is an important foundation for downstream applications, such as object detection, semantic classification and surface reconstruction. Current methods focus on dense point cloud reconstruction for objects but neglect the whole scene. To address this issue, the reconstruction of dense point clouds supervised by inverse stereo matching (IS-Dense) is proposed. In detail, the Transformer model is first used to extract deep features form the point clouds. Second, point cloud features are expanded through the base upsampler. Ultimately, the point clouds would be coordinated following the feature expansion. Due to the uneven distribution of point clouds in the whole scene, some gaps and anomalies are presented in the data. Therefore, a point location refinement module supervised by inverse stereo matching is designed to solve this problem. For this module, the key is to utilize the reconstructed dense point clouds and the right image to estimate the left image. Supervised by real left images, the reconstructed dense point clouds are precise and even-distributed. The experimental results prove the superiority of the proposed method over current methods, especially for the whole scene.