KexianHust / ViTA

ViTA: Video Transformer Adaptor for Robust Video Depth Estimation

KexianHust/ViTA Issues

Projecting to 3d map
Updated 3 months ago
Where can I read the paper?
Updated 4 months ago1
Enhancement: Modifying demo to have VideoCapture take a camera input.
Updated 8 months ago
Does the code for training the model get released?
Updated 9 months ago
with hybrid model i get not correct dictionary .
Updated 9 months ago2
Modifying demo to use image sequences instead of video
Updated a year ago7
Environment.yml
Closed a year ago1
Code release
Closed a year ago4