DeepMill++: Neural Guidance Meets Rasterization for Efficient Accessibility Analysis

摘要

Manufacturability is crucial for reliable product design, with cutter accessibility being a fundamental constraint in subtractive manufacturing. Traditional geometric methods are accurate but computationally expensive, while learning-based approaches often lack conservativeness and generalization, leading to unsafe predictions. In this paper, we introduce DeepMill++, a conservative and highly efficient framework for cutter accessibility analysis on arbitrary triangular meshes. Instead of relying on neural networks as end-to-end predictors, DeepMill++ reformulates accessibility and occlusion detection as a rasterization-based visibility and depth pooling problem, enabling fast and controllable geometric verification on the GPU. A neural network is used only to guide the evaluation order of cutter directions and vertices, significantly reducing redundant computations while preserving strict conservativeness. Experiments show that DeepMill++ achieves up to 9.5× speedup over state-of-the-art geometric methods under matched accuracy, while maintaining 97.5% conservative accessibility accuracy. For meshes up to 125K triangles, full analysis completes in 2.9 seconds, enabling interactive design and large-scale path planning. The method supports general mesh types and diverse cutter sizes without category assumptions.