DA3METRIC-LARGE is an open-source computer-vision model for estimating metric and relative depth from monocular images. It provides sky segmentation and pose-estimation capabilities and can be used locally through a Python API or command-line interface.
DA3METRIC LARGE is an Other AI project. It focuses on estimating real-world scene depth and geometry from monocular images for computer-vision applications. It is built as an open-source project for computer-vision developers and researchers. DA3METRIC LARGE is open source under the Apache-2.0 license. It ships for the web and the command line, and it can be self-hosted.
ByteDance Seed builds and maintains DA3METRIC LARGE, and it first shipped in 2025. The project is developed in the open on GitHub with 6.1k stars and 3 commits in the last 90 days. Key capabilities include metric depth estimation, relative depth estimation, and sky segmentation.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do