FRPSS: Feature Rearrangement in Pre-Shape Space for Single-Image Generation

2026-09-14

AI Summary

本文提出FRPSS方法，通过在预形状空间中重新排列特征并结合MSR-FAGS模块和CLIP-SSPE策略，解决单图像生成中全局结构完整性和局部多样性之间的平衡问题。

Abstract

Generative models trained on a single image often struggle to balance global structural integrity and local diversity. Existing single-image generation methods commonly rely on random noise to drive the generation process and lack explicit global structural constraints, making the generated results prone to spatial structural misalignment when structural variations occur. To address the issue, Feature Rearrangement in Pre-Shape Space for Single-Image Generation (FRPSS) is proposed in this paper. The core of FRPSS is the Manifold Structural Rearrangement with Feature Augmentation on Geodesic Surface (MSR-FAGS) module. MSR-FAGS replaces the randomly initialized features of the low-scale generator with rearranged Pre-Shape features and uses the features to guide image generation at subsequent scales, thereby reducing the risk of structural misalignment. To support downstream tasks such as stylization, a Scale-adaptive Sliding-window Patch Extraction (SSPE) strategy is further designed, and a directional Contrastive Language-Image Pre-training supervision module with SSPE (CLIP-SSPE) is constructed. Qualitative and quantitative experiments demonstrate that FRPSS achieves the best Single Image Fréchet Inception Distance (SIFID) scores on all three datasets while maintaining competitive Learned Perceptual Image Patch Similarity (LPIPS). Further qualitative experiments verify the effectiveness of FRPSS across multiple downstream tasks with the CLIP-SSPE module.

Problem

• single-image generation
• global structural integrity
• local diversity
• structural misalignment

Innovation

• Feature Rearrangement
• Pre-Shape Space
• MSR-FAGS
• SSPE
• CLIP-SSPE