Depth Anything is a foundation model for monocular depth estimation trained on large-scale unlabeled data. The vitb14 variant uses a Vision Transformer backbone. It produces high-quality relative depth maps from RGB images and is available through the Transformers library and the official GitHub repository.
Depth Anything Vitb14 sits in PulseGate's Other AI category. It focuses on estimating depth from a single image without specialized depth sensors. It is built as an open-source project for developers. Depth Anything Vitb14 is open source under the Open Source license. Depth Anything Vitb14 is available on the web, the command line, and API.
LiheYoung builds and maintains Depth Anything Vitb14, and the product first shipped in 2024.
Latest indexed changes and source events
LiheYoung/depth_anything_vitb14 verified by the PulseGate indexer
Other apps tracked under the same category.
