To improve the effectiveness of existing networks in analyzing point cloud data, we propose a plug-and-play module, PnP-3D, aiming to refine the fundamental point cloud feature representations by involving more local context and global bilinear response from explicit 3D space and implicit features. To thoroughly evaluate our approach, we conduct experiments on three standard tasks, including classification, semantic segmentation, and object detection, selecting three state-of-the-art networks from each task for evaluation. Serving as a plug-and-play module, PnP-3D can significantly boost the performances of established networks. Similarly, we propose the first framework (UCNnet) to employ uncertainty by learning from the data labeling process for RGB-D saliency detection. Inspired by the saliency data labeling process, we propose a probabilistic RGB-D saliency detection network via conditional variational autoencoders to model human annotation uncertainty and generate multiple saliency maps for each input image by sampling in the latent space. We can generate an accurate saliency map based on these multiple predictions with the proposed saliency consensus process. Quantitative and qualitative evaluations on six challenging benchmark datasets against 18 competing algorithms demonstrate the effectiveness of our approach in learning the distribution of saliency maps, leading to a new state-of-the-art in RGB-D saliency detection.