InstancePin adds per-instance coordinate tokens and mask-guided fusion to a frozen layout-to-image diffusion model, improving FID and mIoU on Cityscapes while reducing visual blending of nearby same-category objects.
Advances in neural information processing systems27(2014)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
InstancePin: Instance-Addressable Layout-to-Image Diffusion via Coordinate Pinning
InstancePin adds per-instance coordinate tokens and mask-guided fusion to a frozen layout-to-image diffusion model, improving FID and mIoU on Cityscapes while reducing visual blending of nearby same-category objects.