Andres Moreno Vasquez

I wrote Task Unmanager: keeps killing processes Russian Roulette style, until your machine crashes

So these researchers figured out you can basically hallucinate 3D cities into existence using just satellite photos & a diffusion model. The problem's pretty straightforward: satellites only see rooftops. Building facades? Invisible. Street-level detail? Doesn't exist. But people want flyable 3D environments, which means you need all that occluded geometry. When I worked on google maps photogrammetry, we could only use satellite-based 3D for isolated stuff like the pyramids - anything city-scale required airplane flyovers. Which is fine until you hit aerial-denied regions where you literally can't fly. Huge chunks of the world just unavailable. Their trick is honestly kind of beautiful. They train gaussian splats on satellite views, but as it descends toward ground level, the renders turn to absolute garbage - artifacts everywhere. Instead of fighting this, they just treat those nightmare renders as the input to a diffusion model. Basically - "hey FLUX, fix this mess." Then here's where it gets clever: they generate multiple diffusion samples per view instead of committing to one. Because any single denoising path is probably wrong in 3D space, but if you generate a couple and let the GS optimization find consensus across them, you get actual geometric consistency. They do this in episodes, curriculum style - start high, gradually descend (hence the name Skyfall-GS!). With each iteration the ground-level views get less fucked. By the end you've got real-time flyable cities that look surprisingly real, and the geometry still matches the satellite input. No 3D training data. No street-level photos. Just satellites + diffusion doing what it does best - filling in the blanks. It's like neural scene completion but actually practical, and it unlocks basically the entire world.

Spatial index structures are crucial for fast and efficient processing of geospatial data. Here is a summary of what, how, and why: #gischat #geospatial #DataScience #Database

Mood

Run MATLAB programs right from Visual Studio Code ➡️ spr.ly/60130vnIb

SpatialLM just dropped on Hugging Face Large Language Model for Spatial Understanding

NASA recently published one of the most detailed maps yet of the seafloor based on data captured by the SWOT satellite .

Well, it turns out that this approach used by @sidahuj (genius!) for Blender CAN ALSO BE USED WITH QGIS!!!! So, my friends, I present to you "MCP QGIS," which gives Claude access to use QGIS directly! The era of "vibe mapping" begins. See how it works: #QGIS #AI

This looks like something everyone else knows but me, but I’m going to share it anyway.

🚨 NEW INVESTMENT 🇺🇸 Sequoia led a $190M Series C in Peregrine. Peregrine makes software that helps mission-critical organizations (public safety, law enforcement, government, enterprises) integrate and analyze their data, and build operational applications on top of it.

RailScan Multi-Function Robot: Railway Surface Inspection The RailScan robot is designed for track inspection, using a self-moving platform and precise sensors to quickly detect track defects. It assists track inspectors with nighttime inspections, addressing challenges in traditional manual inspections such as heavy workload, missed detections, and difficult tasks. The robot helps reduce inspection costs, improve efficiency, and enhance safety by identifying potential hazards in the rail track. Video source: @ShenhaoRobotics #robotics #inspection #RailwayRobot #technology #engineering #stem #innovation #robots #automation ----------------------- Wanna get your company on Wevolver too? Learn how: wevlv.co/get-your-compa…

"Incoming transmission!" 📡 Classic Command and Conquer games are now open source—ready for modding, preservation, and innovation! Read more: ea.com/games/command-… Dive into the code: github.com/electronicarts

Why do school maps have to be so ugly? My kids have been filling out maps as part of their homeschool curriculum…but they just look so sterile. So, dad can’t help himself and is stepping in! I won’t be going all out with mountains and jungles and such because it needs to stay clean enough that you can easily write in names without too much visual chaos. But, I want to also add some banners to make it easier for them to see what needs to be filled in. Because that was an issue on the original map. Let me know what you think so far!

🔹Git is a tool, version control is a concept. 🔹Docker is a tool, containerization is a concept. 🔹Kubernetes is a tool, container orchestration is a concept. 🔹SQL is a language, relational databases are a concept. 🔹TensorFlow is a library, machine learning is a concept. 🔹Kafka is a tool, event streaming is a concept. 🔹REST is an architecture, APIs are a concept. #Java

8-bit Legacy

☕☕ A #Coffee Plant #Counting Method Based on Dual-Channel NMS and #YOLOv9 Leveraging UAV #Multispectral Imaging ✍️ Xiaorui Wang et al. 🔗 brnw.ch/21wQSSn

/rĕz″ə-loo͞′shən/ /stŭd′ē/

Semantic Versioning explained

How a Kalman filter works, in pictures ow.ly/QNZXd via @mathupdate

MIT's "Street Fighting Mathematics" This course teaches the art of guessing results and solving problems without doing a proof or an exact calculation. Book: ocw.mit.edu/courses/18-098…