yonseivnl/se-cff

Official implementation of "Stereo Depth from Events Cameras: Concentrate and Focus on the Future" (CVPR 2022)

se-cff's Issues

Code for Event-Intensity Stereo

Dear authors,
Thanks for sharing the code.
I want to know if I can access the Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds code in this repo.

Questions about the Knowledge Transfer block

I know you might be busy right now and will update the code of "Knowledge Transfe" part soon, but I'm just curious and want to know about your design.
The question is, are the latent space representations of $b_{past}$ & $b_{both}$ from the same network? Or do you train two different networks (maybe stereo_matching_net) to get $b_{past}$ and $b_{both}$ for distillation? Have you tried these two different ways and if so, what is the difference?
I'll appreciate it if you could answer my question.

A problem about dataset

Hello author, I want to konw how to get the data part named .csv(such as interlaken_00_a.csv) in the test part of the DSEC.
In the DESC website, I don't see the data part named .csv in the Test Sequences.

Event-Intensity Align

Thank you for your impressive work!
I am working on Event-Intensity Stereo. Could you share how you align the events and intensity images from the event camera and RGB camera on the same side?

Docker image build error when installing pytorch

Docker container image that used this project install latest Miniconda3 for using python, and python version of latest Miniconda3 is python3.10(for now, 11th Jan, 2023).

And pytorch version, to be installed when building image, is 1.9.0 that is matched with CUDA version 11.1.1. Torchvision is also dependent with cu111. Now problem is that, pytorch doesn't support torch1.9.0+cu111 for python version 3.10, same as torchvision.

So Docker image file have to be fixed to install specific version of python, Miniconda3.

18, 20, 21 lines have to be fixed.

RUN wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
RUN mkdir /root/.conda
RUN bash Miniconda3-latest-Linux-x86_64.sh -b
RUN rm -f Miniconda3-latest-Linux-x86_64.sh
RUN conda init bash

to

RUN wget https://repo.anaconda.com/miniconda/Miniconda3-py39_22.11.1-1-Linux-x86_64.sh
RUN mkdir /root/.conda
RUN bash Miniconda3-py39_22.11.1-1-Linux-x86_64.sh -b
RUN rm -f Miniconda3-py39_22.11.1-1-Linux-x86_64.sh
RUN conda init bash

In this example, we download Miniconda3 for python 3.9, and python 3.9 support pytorch version 1.9.0+cu111.

If you want to use another specific version of python or Miniconda3, recommend you to visit the Miniconda3 Download pages. At here, just find the specific version, you want to use, and fix the lines above in Docker file.