DreamTuner: Single Image is Enough for Subject-Driven Generation.

Miao Hua Jiawei Liu Fei Ding Wei Liu Jie Wu Qian He

Published in: CoRR (2023)

Keyphrases

single image
multiple images
shape recovery
light source
image pairs
d scene
partially occluded
shape from shading
structured light
indoor scenes
super resolution
spherical harmonics
higher order
input image
stereo images
outdoor images