Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes
This work improves interactive 3D segmentation for users in computer vision by offering a probabilistic framework with enhanced generalization and uncertainty, though it is incremental as it builds on Neural Processes.
The paper tackles the problem of interactive 3D segmentation by addressing generalization from sparse user clicks and uncertainty quantification, proposing NPISeg3D, which achieves superior segmentation performance with fewer clicks and provides reliable uncertainty estimations on four datasets.
Interactive 3D segmentation has emerged as a promising solution for generating accurate object masks in complex 3D scenes by incorporating user-provided clicks. However, two critical challenges remain underexplored: (1) effectively generalizing from sparse user clicks to produce accurate segmentation, and (2) quantifying predictive uncertainty to help users identify unreliable regions. In this work, we propose NPISeg3D, a novel probabilistic framework that builds upon Neural Processes (NPs) to address these challenges. Specifically, NPISeg3D introduces a hierarchical latent variable structure with scene-specific and object-specific latent variables to enhance few-shot generalization by capturing both global context and object-specific characteristics. Additionally, we design a probabilistic prototype modulator that adaptively modulates click prototypes with object-specific latent variables, improving the model's ability to capture object-aware context and quantify predictive uncertainty. Experiments on four 3D point cloud datasets demonstrate that NPISeg3D achieves superior segmentation performance with fewer clicks while providing reliable uncertainty estimations.