DiffuStereo
DiffuStereo copied to clipboard
This repository is the official implementation of DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Cameras.
多谢大神开源,单对图片的测试没问题,但是多对图片测试缺少了thuman_demo_multi.yaml这个配置文件,能够提供的话感激不尽。 
Hi, thanks for the great work! When will the training code be released?
python -m app.inference --config configs/real_demo.yaml --dataroot thuman_demo --view_list 0 1 $$: No module named app.inference
Thanks for the great work! Will the training code be released?
Hi, thanks for your great work? Is it possible to release your rendering details like camera parameters and tools for the rgb images? Thanks.
Thank you for your impressive work. I had just run the test on 2 views and get a nice result. I would like to know do you have a plan...
Great work! Would you provide some information about the type and count of GPUs used in training the model? Thanks.
Great work! Would you provide some information about the type and count of GPUs used in training the model? Thanks.
Hi author, I am confused about how to get ground truth disparity at forward diffusion stage in inference time. I am trying to think of using this idea to refine...
Hi, Thank for sharing your excellent work! May I ask when will the 5.0 version dataset be available? Sorry for disturbing you.