SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

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 Su

Read original source ↗ Open in workspace

recordType

paper

region

Global