DiffusionDepth
DiffusionDepth copied to clipboard
duanyiqun
PyTorch Implementation of introducing diffusion approach to 3D depth perception
Hi there!Thanks for the great work! I have some questions about data sets and training results. The first is the kitti dataset. I see in the README file that you...
Hi,there,first thanks for your excellent work and the open-source code. I encountered some issues while configuring the environment.After installing the mmdet3d according to readme.md, I always receive an incompatiable version...
How can we test the model with own images only ? What are the pre requisites ?
Dear author, Thank you so much for the amazing work and also providing guidance on how to work with your amazing repo. I would like to convert the code from...
Hi, thanks for your excellent work. I have a few questions. I didn't figure out what is self-diffusion. Is the refined depth map you mentioned in the paper a true...
Hi, thanks for your wonderful work! When I was reading the code, I noticed that you took the time embedding on the feature extracted from the RGB images. I am...
Hi there, great work! Really appreciate that you open source the code so soon! I have some questions about the diffusion and denoising process. The image shown in the README...
Hi, nice work and thanks for the open code. In the 3.3 Section of the paper,there are two Attention applied in the MCDB module,called a self-attention and a channel-wise attention,...
Thanks for ur excellent work! I have a question about ddim loss which is computed with noise and pred noise. The pred noise, which is the output of ScheduledCNNRefine Model...
Why is it that in the paper, rgb is input to get dense depth, while in testing code, rgb, dep, gt is input, which becomes depth completion
