Joint prototype and coefficient prediction for 3D instance segmentation

Abstract

Abstract 3D instance segmentation is crucial for applications demanding comprehensive 3D scene understanding. Here, a novel method is introduced that simultaneously learns coefficients and prototypes. Employing an overcomplete sampling strategy, the method produces an overcomplete set of instance predictions, from which the optimal ones are selected through a Non‐Maximum Suppression (NMS) algorithm during inference. The obtained prototypes are visualizable and interpretable. The method demonstrates superior performance on S3DIS‐blocks, consistently outperforming existing methods in mRec and mPrec. Moreover, it operates 32.9% faster than the state‐of‐the‐art. Notably, with only 0.8% of the total inference time, the method exhibits an over 20‐fold reduction in the variance of inference time compared to existing methods. These attributes render the method well‐suited for practical applications requiring both rapid inference and high reliability.

Keywords

• computer vision
• image processing
• image segmentation
• learning (artificial intelligence)
• neural nets