Pix2NeRF: Unsupervised Conditional $\pi$-GAN for Single Image to Neural Radiance Fields Translation.

Shengqu Cai Anton Obukhov Dengxin Dai Luc Van Gool

Published in: CVPR (2022)

Keyphrases

single image
multiple images
d scene
shape recovery
image pairs
shape from shading
super resolution
structured light
semi supervised
light source
spherical harmonics
computer vision
intrinsic images
light field
image processing
partially occluded
lighting conditions
scene geometry
image segmentation
manhattan world