Record3D mentions (3)

• [R] CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory + Code + Robot demo

  Best part, I believe, is that you should be able to train your own CLIP-Field for your living room if you have an hour, a decent GPU, and a way to get RGB-D video (an iPhone 13 Pro works great!) I hope you can give the code a try: https://github.com/notmahi/clip-fields or check out the website https://mahis.life/clip-fields/ for more interactive demos. Our Arxiv submission is also out now, at... Source: over 1 year ago

• An End-to-End Guide to Photogrammetry with Mobile Devices

  If you don't need publication-quality 3D models, the latest iPhones have built-in LIDAR sensors, both front (for facial recognition) and back (for AR). There are a variety of apps that can use these built-in sensors to build 3D models of the environment in what I think is a pretty painless and intuitive way. The results aren't publication-quality like the NYTimes' guide's results but it's quick, easy and "good... - Source: Hacker News / over 2 years ago

• Show HN: Object Detection in an Hour

  Maybe worth to support front camera (TrueDepth camera) as well? Record3d gives pretty good accuracy (https://record3d.app/). I know probably not the best way to scan something without seeing the screen but better that than nothing. As a workaround people can use small mirror as well to do scanning and see result on the screen at the same time. - Source: Hacker News / almost 3 years ago

LostGeometry.xyz mentions (0)