SingleInsert: Inserting New Concepts from a Single Image into Text-to-Image Models for Flexible Editing.

Zijie Wu Chaohui Yu Zhen Zhu Fan Wang Xiang Bai

Published in: CoRR (2023)

Keyphrases

single image
multiple images
shape recovery
d scene
outdoor images
image pairs
partially occluded
information from multiple images
super resolution
scene geometry
light source
spherical harmonics
indoor scenes
multi view
fundamental problem in computer vision
scene understanding
shape from shading
image processing