Hey HN,<p>I built depthviz, an open-source CLI tool that generates depth & time overlay videos from dive logs. It supports dive computers (Garmin, Suunto, Shearwater, Apnealizer) and manual input for freedivers who want to enhance their footage with real-time dive data.<p>Why I Built It:<p>Adding dive data to videos manually is tedious. depthviz automates this by reading dive logs (.fit, .csv, .xml) from various sources, generating an overlay video with real-time depth, allowing full customization (fonts, colors, depth smoothing, stroke width), and running on Windows, macOS, and Linux.<p>How It Works:<p>Export a dive log from a dive computer or create a manual CSV. Run a single command. Then import the overlay into CapCut, Premiere Pro, DaVinci Resolve, etc.<p>Looking for Feedback On:<p>README – Is it clear, engaging, and well-structured? (Most wanted!) / Installation & Usability – Is the setup intuitive enough? / or Anything you'd expect from a tool like this?<p>GitHub: <a href="https://github.com/noppanut15/depthviz">https://github.com/noppanut15/depthviz</a><p>Would love to hear your thoughts!
I wonder if you develop an ML model that uses brightness and color reduction cues in the video in order to estimate depth in lieu of a dive computer. I suspect cameras auto-exposure or underwater modes may nullify this.