Diffusion-generated image-to-video transformations produce realistic optical flows that, when used as training data, push video salient object detection to new state-of-the-art results on DAVIS, FBMS, DAVSOD, and ViSal.
Video generation models as world simulators
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
-
Transforming Static Images Using Generative Models for Video Salient Object Detection
Diffusion-generated image-to-video transformations produce realistic optical flows that, when used as training data, push video salient object detection to new state-of-the-art results on DAVIS, FBMS, DAVSOD, and ViSal.