Spatially-Guided Self-Attention Refinement for Zero-Shot Hair Segmentation (Student Abstract)
Abstract
Recent advances in Stable Diffusion have extended its applications beyond image generation, such as zero-shot segmentation. In this work, we propose a training-free method that leverages both self- and cross-attention maps to achieve fine-grained hair segmentation. The proposed approach achieves promising fine-grained results without additional training.
Fields of Study & Subjects
Face recognition and analysis
Advanced Neural Network Applications
Generative Adversarial Networks and Image Synthesis
Publication details
- Journal / source
- Underline Science Inc.
- Publication date
- 7 January 2026
- Language
- EN