This repository acquires continuous frame sequences through cameras mounted on drones and uses an end-to-end feedforward deep learning architecture to directly regress three-dimensional geometric representations from two-dimensional images.
Film your basement on your phone and find out if it can become a legal second home anywhere in Ontario, then get the layout, permit set and money to build it. Built for the Meta AI hackathon on SAM 3.1, Muse Spark, Muse Wonder, Muse Image, Muse Voice Transcribe and MapAnything.
A unified, feed-forward model integrating the MapAnything 3D reconstruction backbone with Mask2Former for multi-view consistent panoptic segmentation. This approach provides feature-rich and metric accurate semantic maps for indoor robot navigation while eliminating the need for posed inputs and costly test-time optimization.
Voice-first 3D memory of your home. Built first for blind and low-vision people, useful to anyone. Scan a room once with an iPhone (LiDAR + Meta models), then ask “where are my keys?” and hear step-by-step directions. SAM 3.1, MapAnything and Muse Spark Open on Baseten. Meta Global AI Developer Hackathon, Oct 26 to Nov 4, 2026.
To associate your repository with the mapanything topic, visit your repo's landing page and select "manage topics."