ViewDelta uses text prompts to define relevant scene changes, enabling one model to work across multiple change-detection datasets and view angles.
The change you want to see (now in 3d)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
ViewDelta: Scaling Scene Change Detection through Text-Conditioning
ViewDelta uses text prompts to define relevant scene changes, enabling one model to work across multiple change-detection datasets and view angles.