From Photos to Positions: Prototyping VLM-Based Indoor Maps
Just a fun hack I did while bored over the weekend. My wife was busy shopping, it got me thinking that can VLMs solve the indoor location problem in a mall? Can I just show a VLM a map and an image and have it doa good enough job locating me? I hacked this P.O.C and it seems to work.
From Photos to Positions: Prototyping VLM-Based Indoor Maps launched on July 5, 2025 with 55 votes, #558 of 9,223 launches that month and more than 90% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
This project explores using vision language models to determine a user's indoor location by analyzing a photo and comparing it against a map image. Created as a weekend prototype, it tests whether VLMs can accurately pinpoint positions within indoor spaces like shopping malls without specialized positioning infrastructure. The proof-of-concept demonstrates that the approach shows promise for solving indoor navigation challenges where traditional GPS fails.
written from the facts on this page · September 2026
From the sources
Disclaimer: This project was completed entirely on personal time and hardware. It is not affiliated with, endorsed by, or representative of any institutions or organizations with which I am affiliated. The views and opinions expressed herein are solely my own and do not represent those of my employer or any associated institutions. LLMs and VLMs have been eating the world. Last week, I listened to a talk by Andrej Karpathy on his view of "Software 3.0." Unlike the two extreme perspectives I'm usually surrounded by, Andrej’s talk was refreshingly optimistic—without ignoring the pitfalls of LLMs. It took me back to 2014, when I took on my first paid gig. I was still in high school and had…from arjo129.github.io
Does a similar job
all alternatives →
Satellite imagery object detection using text promptsMar 2026 · useful-ai-tools.com · ▲53I built a browser-based tool for detecting objects in satellite imagery using vision-language models (VLMs). You draw a polygon on the map and enter a text prompt such as "swimming pools", "oil tanks", or "buses". The system scans the selected area tile-by-tile and returns detections projected back onto the map as GeoJSON. Pipeline: select area and zoom level, split the region into mercantile tiles, run each tile with the prompt through a VLM, convert predicted bounding boxes to geographic coordinates (WGS84), and render the results back on the map. It works reasonably well for distinct…
fast visual-inertial odometry/SLAM for AR/VR/Robotics2019 · github.com · ▲102X Inertial-aided Visual Odometry. Contribute to ucla-vision/xivo development by creating an account on GitHub.
Visual inference exploration and experimentation playground2024 · github.com · ▲46Most inference UIs that I've come across pretty much just give us a chat-like interface to toy around with models in a single visual conversation thread. Given the fact that we are limited to seeing only one output at a time, it's kind of hard to compare outputs from different models, adjustments made to the prompting, and sampler settings. But even when keeping the generation parameters the same (e.g., to test for reliability in the output) and just going for multiple passes, there is no easy way to have a side-by-side comparison to keep track of the outputs from the multiple "rounds". I…
More work this month
the category →
Endless lofi beats composed live in your browser, over pixel-art nights in Paris, Tokyo, New York, Hong Kong, Sydney, San Francisco and more. Free, no sign-up.
Work · 26d ago · loficities.com
Smooth Recorder▲257Mac screen recordings that look edited when you hit stop
Work · 20d ago · smoothrecorder.com
Work · 14d ago · readrare.com
Source: Show HN post ↗
Launched alongside, July 2025
the whole month →
Trickle - Magic Canvas ▲1,064Hey HN! Introducing Trickle Magic Canvas: the world’s first Agentic Canvas, where you can visually co-create apps and websites with AI, from idea to production. Why is a canvas better? Most AI tools today rely on linear chats or text prompts. We believe that limits creativity and clarity. Canvas changes the game. 1. Every version & page at a glance. Each page and sub-page lives on a timeline. You can quickly browse, edit, and preview progress like a living, visual document — no more digging through chat logs or scattered states. 2. The canvas is the context. Unlike linear chats, you can…
AI · 2025 · trickle.so
- TB
Life & fun · 2025 · trytender.app
Today marks ten years, 3653 consecutive days, of running at least one mile every day under the USRSA rules [1]. To celebrate, I built an interactive dashboard that turns a decade of GPX files into charts you can explore. Running has truly changed my life: I've made lifelong friends, explored beautiful places, and more importantly invested into my own health and fitness, which I'm starting to see the positive benefits as I get older. The stack is pretty simple: a NextJS app, with a Postgres database to keep all my running data, and all the stats are pre-computed and cached in Redis, so I…
Dev tools · 2025 · nodaysoff.run
Made this website as an exercise in vibe-coding and GCP. It was posted about a few times around the internet, on sites like Morning Brew (https://www.morningbrew.com/issues/business-buzzkill), MetaFilter (https://www.metafilter.com/209703/Draw-A-Fish), boingboing.net, etc. I think it's cute! I built a basic CNN trained against penises and swastikas, and then anything that doesn't hit the 63% confidence score gets sent to a mod queue, a vibe-coded fish-tinder…
AI · 2025 · drawafish.com
Hi HN - I made a site that takes a UK postcode, grabs the local MP's information and generates an AI mockup of what their ID might look like. It's a small, silly protest at the stupidity of the Online Safety Act that just came into force. edit - My open AI credits got hugged to death, please use a known postcode (like one from Kier Starmer's constituency, WC2B6NH) in the meantime.
AI · 2025 · use-their-id.com