CompletionFormer
CompletionFormer copied to clipboard
youmi-zym
[CVPR2023] CompletionFormer: Depth Completion with Convolutions and Vision Transformers
Hi , sorry to bother you, I'm wondering when evaluation on the KITTI test server, have you met with the file size over 500MB problem? Cause the website requests the...
Hi, I would like to inquire about the rgb images I read while training my dataset. The rgb images saved during the training process all have a gray layer, but...
During the learning process, the following error occurs and learning is interrupted. The only change I made was changing the gpus from [0,1,2,3] to [0].The following is a description of...
When I train on the single GPU, it shows the error in the main.py in line255: UnboundLocalError:local variable 'sample' referenced before assignment
Hello, may I ask if it's not possible to train if I only have a sparse depth map?
Dear authors, Thank you for releasing this impressive and valuable work! I want to inquire whether CompletionFormer can handle the task with only sparse depth as input? Thank you for...
I have an ubuntu 24.04 which support cuda 12.9, I can not use cuda 11.3 Have you tested the code for cuda 12.9? How to prepare the environment with cuda...
Hi, thank you for sharing CompletionFormer! I am working on a depth completion task for tea leaf scenes (RGB + RealSense depth). The data are mostly dense but contain small...
