AAAI 2026technical0 citations

Spatially-Guided Self-Attention Refinement for Zero-Shot Hair Segmentation (Student Abstract)

Suin Kim, Jihoon Lee, Moonsung Kang, Doheun Cha, Sangtae Ahn

Abstract

Recent advances in diffusion-based models have significantly broadened their scope, extending well beyond image generation to encompass zero-shot segmentation tasks. In this work, we introduce a novel, training-free approach that harnesses both self- and cross-attention maps to achieve highly detailed hair segmentation. Our method demonstrates remarkable efficacy in producing fine-grained results without the need for additional training.

BibTeX
@inproceedings{aaai2026_spatiallyguideds,
  title = {Spatially-Guided Self-Attention Refinement for Zero-Shot Hair Segmentation (Student Abstract)},
  author = {Suin Kim and Jihoon Lee and Moonsung Kang and Doheun Cha and Sangtae Ahn},
  booktitle = {AAAI 2026},
  year = {2026}
}