Bingxin Ke

Thanks for your interest in our work. We do have a plan to release training and evaluation code in the future. However, the schedule is not clear yet. Please stay...

I've started refactoring and cleaning the code (in my part-time 💪) and will release it as soon as it's ready and tested.

I'm working on it. coming soon

Training code has been released.

Hello, thanks for reporting the issue. This is not supposed to happen since the command you used would automatically resize the input image and will only use

There is a trick to improve temporal consistency. Please check out our [tutorial on Diffusers](https://huggingface.co/docs/diffusers/using-diffusers/marigold_usage#frame-by-frame-video-processing-with-temporal-consistency) for details.  

> > Hi, > > Thank you for your interest in Marigold and the generation of 3D point clouds from it. > > Please note that Marigold predicts affine invariant...

Thanks for your interest in our work. As we addressed in the Section 4.1 of our [paper](https://arxiv.org/pdf/2312.02145.pdf), we use gradient accumulation to account for the memory pressure during training: >...

> > Thanks for your interest in our work. As we addressed in the Section 4.1 of our [paper](https://arxiv.org/pdf/2312.02145.pdf), we use gradient accumulation to account for the memory pressure during...

Hi, we didn't use fp16 during training.