DG-NBV: A Cognitive Framework for Direct Generation of Next Best View in Continuous View Space

The next best view (NBV) plays an important role in the 3-D object reconstruction. Existing NBV methods mainly adopt the generate-and-test strategy to select the best view in the discrete view space. This affects the adaptation to diverse objects. To solve this problem, a new NBV paradigm to directly generate the NBV in the continuous view space according to the input point cloud is proposed. Specifically, a point cloud feature extraction module with learnable view and position tokens is presented. These tokens are added to the neighborhood and the position features of the point cloud to fully mine global contextual information, enhancing the feature representation. The predicted view from the proposed network is linked to a pretrained view evaluation network. By duplicating this prediction view and then concatenating the duplication result with the extracted point cloud feature, the evaluation network is endowed with the ability to evaluate arbitrary views. Take the evaluation score of the evaluation network corresponding to the predicted view as the supervision signal, the network is trained. In this way, an effective solution of the NBV selection in the continuous view space is obtained. Accordingly, the adaptability to different objects is reinforced. Experimental results on the ShapeNet and MIT CSAIL datasets demonstrate the effectiveness of the proposed method.