Pose-Star: Anatomy-Aware Editing for Open-World Fashion Images

TL;DR

Pose-Star introduces an anatomy-aware, pose-robust framework for fashion image editing that enhances mask controllability and localization in complex poses, enabling more flexible and precise edits in real-world scenarios.

Contribution

The paper proposes Pose-Star, a novel framework that redefines mask generation with anatomy-aware structures and pose robustness, addressing limitations of existing methods.

Findings

Improves mask controllability for user-defined fashion edits.

Enhances pose robustness in complex articulated poses.

Achieves more precise localization of rare body regions.

Abstract

To advance real-world fashion image editing, we analyze existing two-stage pipelines(mask generation followed by diffusion-based editing)which overly prioritize generator optimization while neglecting mask controllability. This results in two critical limitations: I) poor user-defined flexibility (coarse-grained human masks restrict edits to predefined regions like upper torso; fine-grained clothes masks preserve poses but forbid style/length customization). II) weak pose robustness (mask generators fail due to articulated poses and miss rare regions like waist, while human parsers remain limited by predefined categories). To address these gaps, we propose Pose-Star, a framework that dynamically recomposes body structures (e.g., neck, chest, etc.) into anatomy-aware masks (e.g., chest-length) for user-defined edits. In Pose-Star, we calibrate diffusion-derived attention (Star tokens) via skeletal keypoints to enhance rare structure localization in complex poses, suppress noise through phase-aware analysis of attention dynamics (Convergence,Stabilization,Divergence) with threshold masking and sliding-window fusion, and refine edges via cross-self attention merging and Canny alignment. This work bridges controlled benchmarks and open-world demands, pioneering anatomy-aware, pose-robust editing and laying the foundation for industrial fashion image editing.