Login / Signup
PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss.
Juan Luis Gonzalez Bello
Munchurl Kim
Published in:
CoRR (2021)
Keyphrases
</>
single view
pixel level
multi view
depth estimation
depth map
dynamic scenes
multiple views
foreground objects
image fusion
stereo vision
surface reconstruction
d scene
high quality
stereo matching
stereo pair
superpixels
image registration