在1MB内存内实现高精度线条检测，专为嵌入式设备优化。
MiLSD: A Micro Line-Segment Detector for Resource-Constrained Devices
- 采用轻量全卷积结构，设计中心+长度+角度的输出形式
- 8位量化保持性能，4位量化导致角度回归严重退化
- 适合资源受限的嵌入式视觉系统部署
线段检测是视觉SLAM、3D重建和工业检测的关键组件。近年来深度学习方法显著提升了精度，但即使是最小模型也需数兆内存，超出低成本MCU容量。本文研究在1MB以下内存预算下的最高可达成精度。提出MiLSD，一种专为MCU级约束设计的检测器，在紧凑的全卷积骨干网络中系统比较三种输出表示。结果表明，提出的F-Clip（中心+长度+角度）形式在小模型下学习效果最佳。8位量化可保留全精度性能，而4位量化导致显著退化，尤其在角度回归上；量化感知训练仅部分恢复损失。在1MB激活内存预算下，结合亚像素解码、测试时增强和轻量验证器，MiLSD将ShanghaiTech Wireframe数据集上的sAP10从10.6（25k参数，0.25MB）提升至24.1。本文不追求与GPU级解析器竞争，而是绘制嵌入式视觉系统中精度-内存权衡的完整图谱，涵盖表示方式、比特宽度、容量及后处理策略。
原文摘要 · Abstract (English)
Line segment detection is a key building block in visual SLAM, 3D reconstruction, and industrial inspection. Recent deep learning methods have greatly improved accuracy, yet even the smallest models require several megabytes of memory, exceeding low-cost MCU capacity. This work investigates the maximum achievable accuracy under a sub-megabyte budget. We propose MiLSD, a detector tailored for MCU-level constraints, and systematically compare three output representations within a compact fully-convolutional backbone. Our study shows that the proposed F-Clip center-with-length-and-angle formulation learns most effectively at small model sizes. We find that 8-bit quantization preserves full-precision performance, while 4-bit quantization causes significant degradation, particularly in angle regression, with quantization-aware training recovering only part of the loss. With a one-megabyte activation budget and inference enhancements including sub-pixel decoding, test-time augmentation, and a lightweight verifier, MiLSD improves sAP10 on ShanghaiTech Wireframe from 10.6 (25k parameters, 0.25 MB) to 24.1 within 1 MB. Rather than competing with GPU-scale parsers, we map the accuracy memory trade-off across representations, bit-widths, capacities, and post-processing strategies for embedded vision systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。