用螺旋采样压缩图像，高速低带宽下仍能保持结构清晰
Double-Helix Vision (DH-V2): A Geometry-Based Visual Sampler for Bandwidth-Constrained Perception
- 双螺旋轨迹按黄金比例采样，中心密周边疏，仿生视觉聚焦
- 4K图压缩1433倍，保留几何结构，1080p下仅需0.52毫秒处理
- 无需神经网络，适合嵌入式机器人等资源受限场景
我们提出双螺旋视觉（DH），一种基于几何的图像采样方法，通过一对相位偏移180度的黄金比例螺旋轨迹，将二维图像压缩为紧凑的一维信号。不同于均匀处理每个像素，DH采用生物启发的中央聚焦机制：中心高密度采样，边缘稀疏覆盖。在4K分辨率下，实现1433倍压缩比（99.93%数据减少），同时保留场景几何结构。完整感知流程——包括空间映射、时间碰撞检测和帧内结构视差估计——在纯CPU硬件上以1080p运行时仅需0.52毫秒，且无需依赖神经网络。在极端采样预算（每螺旋128点）下，于CIFAR-10上较均匀随机采样提升6.03%准确率。提供可序列化的机器人API，每包仅2.7KB，响应时间低于毫秒级。代码与基准测试已开源，采用MIT许可证。
原文摘要 · Abstract (English)
We present Double-Helix Vision (DH), a geometry-based visual sampler that compresses 2D images into compact 1D signals using paired golden-ratio-inspired spiral trajectories. Rather than processing every pixel uniformly, DH employs two phase-shifted helices (Alpha and Beta, offset by 180 degrees) to sample the image with biologically-inspired foveation: high density at the center, sparse coverage at the periphery. At 4K resolution, DH achieves a 1,433x compression ratio (99.93% reduction) while preserving the geometric structure of the scene. The full perception pipeline -- including spatial mapping, temporal collision detection, and intra-frame structural disparity estimation -- runs in 0.52 ms at 1080p on CPU-only hardware, with no neural network dependencies. On CIFAR-10 at extreme sampling budgets (K=128 points per helix), DH achieves a +6.03% accuracy gain over uniform random sampling. A JSON-serializable Robotics API is provided, delivering sub-millisecond spatial perception reports in 2.7 KB packets. Code and benchmarks are available under the MIT License.
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。