DriveEditor uses depth-aware 3D bounding box projection and single-reference appearance cues to reposition, replace, remove, and insert objects in driving videos with a single diffusion framework.
H.; Vora, S.; Liong, V
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes
DriveEditor uses depth-aware 3D bounding box projection and single-reference appearance cues to reposition, replace, remove, and insert objects in driving videos with a single diffusion framework.