Post
Introducing Marigold πΌ - a universal monocular depth estimator, delivering incredibly sharp predictions in the wild! Based on Stable Diffusion, it is trained with synthetic depth data only and excels in zero-shot adaptation to real-world imagery. Check it out:
π€ Hugging Face Space: https://huggingface.co/spaces/toshas/marigold
π€ Hugging Face Model: https://huggingface.co/Bingxin/Marigold
π€ Hugging Face Paper: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation (2312.02145)
π Website: https://marigoldmonodepth.github.io
πΎ Code: https://github.com/prs-eth/marigold
πΎ Code:
π Paper: https://arxiv.org/abs/2312.02145
Brought to you by the fantastic team from the Photogrammetry and Remote Sensing group of ETH Zurich: Bingxin Ke ( @Bingxin ), Anton Obukhov ( @toshas ), Shengyu Huang, Nando Metzger ( @nandometzger ), Rodrigo Caye Daudt, and Konrad Schindler.
π€ Hugging Face Space: https://huggingface.co/spaces/toshas/marigold
π€ Hugging Face Model: https://huggingface.co/Bingxin/Marigold
π€ Hugging Face Paper: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation (2312.02145)
π Website: https://marigoldmonodepth.github.io
πΎ Code: https://github.com/prs-eth/marigold
πΎ Code:
pip install diffusers
(check comments to this post for details!)π Paper: https://arxiv.org/abs/2312.02145
Brought to you by the fantastic team from the Photogrammetry and Remote Sensing group of ETH Zurich: Bingxin Ke ( @Bingxin ), Anton Obukhov ( @toshas ), Shengyu Huang, Nando Metzger ( @nandometzger ), Rodrigo Caye Daudt, and Konrad Schindler.