Feature detection exploration in Lidar DEMs via differential decomp
I'm not a geospatial expert — I work in AI/ML. This started when I was exploring LiDAR data with agentic assitince and noticed that different signal decomposition methods revealed different terrain features. The core idea: if you systematically combine decomposition methods (Gaussian, bilateral, wavelet, morphological, etc.) with different upsampling techniques, each combination has characteristic "failure modes" that selectively preserve or eliminate certain features. The differences between outputs become feature-specific filters. The framework tests 25 decomposition × 19 upsampling…
Feature detection exploration in Lidar DEMs via differential decomp launched on January 1, 2026 with 8 votes, #1,339 of 14,584 launches that month and more than 75% of that year's launches.
What it does
Multi-method differential feature detection in Digital Elevation Models. 25 decomposition x 19 upsampling methods reveal features invisible in raw terrain data. Built for archaeological prospection (Hopewell Road, Newark Earthworks) and general terrain analysis. - bshepp/RESIDUALS
In the maker’s words, at launch
I'm not a geospatial expert — I work in AI/ML. This started when I was exploring LiDAR data with agentic assitince and noticed that different signal decomposition methods revealed different terrain features. The core idea: if you systematically combine decomposition methods (Gaussian, bilateral, wavelet…
Does a similar job
all alternatives →
Automated smooth Nth order derivatives of noisy data2024 · github.com · ▲146This little project came about because I kept running into the same problem: cleanly differentiating sensor data before doing analysis. There are a ton of ways to solve this problem, I've always personally been a fan of using kalman filters for the job as its easy to get the double whammy of resampling/upsampling to a fixed consistent rate and also smoothing/outlier rejection. I wrote a little numpy only bayesian filtering/smoothing library recently (https://github.com/hugohadfield/bayesfilter/) so this felt like a fun and very useful first thing to…
Every mountain, building and tree shadow mapped for any date and time2024 · shademap.app · ▲685I've been working on this project for about 4 years. It began as terrain only because world wide elevation data was publicly available. I then added buildings from OpenStreetMap (crowd sourced) and more recently from Overture Maps data. Some computer vision/machine learning advancements [1] in the past few years have made it possible to estimate tree canopy heights using satellite imagery alone making it possible to finally add trees to the map. The data isn't perfect, but it's within +/- 3 meters of so. Good enough to give a general idea for any location on Earth. Happy to answer…
Boldly go where Gradient Descent has never gone before with DiscoGrad2024 · github.com · ▲232Trying to do gradient descent using automatic differentiation over branchy programs? Or to combine them with neural networks for end-to-end training? Then this might be interesting to you. We develped DiscoGrad, a tool for automatic differentiation through C++ programs involving input-dependent control flow (e.g., "if (f(x) < c) { ... }", differentiating wrt. x) and randomness. Our initial motivation was to enable the use of gradient descent with simulations, which often rely heavily on such discrete branching. The latter makes plain autodiff mostly useless, since it can only account for the…
High-resolution surface analysis with Lidar data2025 · github.com · ▲66High-resolution surface analysis with LiDAR data. Contribute to r-follador/delta-relief development by creating an account on GitHub.
- IEInteractively explore different map projections2017 · mjmdavis.com · ▲109
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
