Marigold
Marigold copied to clipboard
prs-eth
[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
I am currently attempting to reproduce the training process described in your paper using Stable Diffusion v2. However, my RTX 4090 ran out of memory when training with batchsize 32...
Thank you for the great work. I am planning to train this model on depth images from different domains and also try training on other problem statements like semantic segmentation....
Hello everybody, I have come across this issue while experimenting with the VAE depth decoder ‘decode_depth’ and the single inference function ‘single_infer’. The VAE decoder is not bound to the...
Awesome Work~ The foreground effect of the depth estimation is very good, even better than SAM ，Have you considered applying it to the field of saliency detection? 
The `run.py` now can read EXR files and write EXR files. It creates an extra folder for saving the EXR with float32 precision, which are ready to be used in...
- Adds `pyproject.toml` and `setup.py` files which allows for `pip install`. - Move files into `src` so that internally and externally functionality can be imported with eg `from marigold.model.rgb_encoder import...
First: I had to disable the `enable_xformers` flag, for the cases where cuda is not available.
Thanks for the work you've done on Marigold. This is a revolutionary depth map estimator with extreme details compared to previous methods. Imo, one noticable application of it is [ControlNet](https://arxiv.org/pdf/2302.05543.pdf)...
Depth maps generated from video frames by Marigold is obiviously flickering. While this can be partially fixed by setting high n_repeat and fixed seed, such method is inefficent imo. Is...