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

arXiv: https://arxiv.org/abs/2609.16594 · HTML: https://mlsanity.com/paper/2609.16594/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation](https://mlsanity.com/paper/2110.02711/) (2021)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Splicing ViT Features for Semantic Appearance Transfer](https://mlsanity.com/paper/2201.00424/) (2022)
- [CLIPstyler: Image Style Transfer with a Single Text Condition](https://mlsanity.com/paper/2112.00374/) (2021)
- [Improved Techniques for Training Single-Image GANs](https://mlsanity.com/paper/2003.11512/) (2020)
- [SinDDM: A Single Image Denoising Diffusion Model](https://mlsanity.com/paper/2211.16582/) (2022)
- [SinFusion: Training Diffusion Models on a Single Image or Video](https://mlsanity.com/paper/2211.11743/) (2022)
- [InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation](https://mlsanity.com/paper/2407.00788/) (2024)
- [Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models](https://mlsanity.com/paper/2103.15545/) (2021)
- [Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample](https://mlsanity.com/paper/2006.12226/) (2020)
- [SinDiffusion: Learning a Diffusion Model from a Single Natural Image](https://mlsanity.com/paper/2211.12445/) (2022)
- [Generating natural images with direct Patch Distributions Matching](https://mlsanity.com/paper/2203.11862/) (2022)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [PetsGAN: Rethinking Priors for Single Image Generation](https://mlsanity.com/paper/2203.01488/) (2022)
- [ExSinGAN: Learning an Explainable Generative Model from a Single Image](https://mlsanity.com/paper/2105.07350/) (2021)
- [MOGAN: Morphologic-structure-aware Generative Learning from a Single Image](https://mlsanity.com/paper/2103.02997/) (2021)
- [Deep Internal Learning: Deep Learning from a Single Input](https://mlsanity.com/paper/2312.07425/) (2023)
- [A Kendall Shape Space Approach to 3D Shape Estimation from 2D Landmarks](https://mlsanity.com/paper/2207.12687/) (2022)
- [StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation](https://mlsanity.com/paper/2604.12575/) (2026)
- [Efficient and Training-Free Single-Image Diffusion Models](https://mlsanity.com/paper/2606.04299/) (2026)

## Abstract (arXiv)

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 Fr'echet 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.