Show HN: Feature detection exploration in Lidar DEMs via differential decomp
created: Jan. 1, 2026, 12:29 a.m. | updated: Jan. 1, 2026, 7:34 p.m.
RESIDUALS: Multi-Method Differential Feature DetectionA framework for feature detection in Digital Elevation Models using systematic decomposition and differential analysis.
RESIDUALS systematically tests combinations of signal decomposition and upsampling methods to identify which combinations best reveal features in elevation data.
Exhaustive Parameter Exploration# Run all 39,731 parameter combinations python run_exhaustive.py --output results/exhaustive # Limited test run python run_exhaustive.py --max-decomp 2 --max-upsamp 2Generates comprehensive documentation of all method combinations with statistics and hashes.
Output VisualizationThe main output is a grid showing:Rows : Decomposition methods: Decomposition methods Columns: Upsampling methods + ground truth comparisons + divergence metricsEach cell reveals different features.
The Δ columns show where each method matches or misses ground truth features.
23 hours, 57 minutes ago: Hacker News