Uncertainty Estimation for 3D Dense Prediction via Cross-Point Embeddings

Dense prediction tasks are common for 3D point clouds, but the uncertainties inherent in massive points and their embeddings have long been ignored. In this work, we present CUE, a novel uncertainty estimation method dense clouds. Inspired by metric learning, key idea of CUE is to explore cross-point upon conventional pipeline. Specifically, involves building probabilistic embedding model then enforcing alignments space. We also propose CUE+, which enhances explicitly modeling dependencies covariance matrix. demonstrate that both CUE+ generic effective clouds with two different tasks: (1) geometric feature learning first time obtain well-calibrated uncertainty, (2) semantic segmentation reduce uncertainty's Expected Calibration Error state-of-the-arts 16.5%. All estimated without compromising predictive performance.