By counting Markov-chain hitting times in Stable Diffusion attention, M2N2 performs training-free interactive segmentation that outperforms trained unsupervised methods on three of four benchmarks.
Geodesic matting: A frame- work for fast interactive image and video segmentation and matting
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
-
Repurposing Stable Diffusion Attention for Training-Free Unsupervised Interactive Segmentation
By counting Markov-chain hitting times in Stable Diffusion attention, M2N2 performs training-free interactive segmentation that outperforms trained unsupervised methods on three of four benchmarks.