ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene
Editing
Work
Year: 2024
Type: preprint
Abstract: This paper proposes ConsistDreamer - a novel framework that lifts 2D diffusion models with 3D awareness and 3D consistency, thus enabling high-fidelity instruction-guided scene editing. To overcome th... more
Source: arXiv (Cornell University)
Cites:
Cited by:
Related to: 10
Citation percentile (by year/subfield):
Topic: Advanced Vision and Imaging
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green