ViTA: Video Transformer Adaptor for Robust Video Depth Estimation.

Ke Xian Juewen Peng Zhiguo Cao Jianming Zhang Guosheng Lin

Published in: IEEE Trans. Multim. (2024)

Keyphrases

video sequences
video data
depth estimation
dynamic scenes
video frames
real time
space time
depth map
event detection
stereo vision
high quality
semi supervised