Marigold Depth v1-0 is a diffusion model developed by ETH Zurich's Photogrammetry and Remote Sensing Lab for predicting depth from single RGB images in a zero-shot manner. It works across diverse scenes without fine-tuning and integrates easily with the Diffusers library. The model is useful for 3D reconstruction, robotics, and augmented reality applications.
Marigold Depth V1 0 sits in PulseGate's Other AI category. It focuses on estimating accurate depth maps from single images without task-specific training data or camera calibration. Marigold Depth V1 0 is an open-source project aimed at developers. The project is open source (Apache-2.0). It ships for the web, the command line, and API.
Behind Marigold Depth V1 0 is Photogrammetry and Remote Sensing Lab of ETH Zurich, based in Switzerland, and it first shipped in 2023. Development happens publicly on GitHub with 3.2k stars.
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