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

• URL: http://arxiv.org/abs/2609.16594v1
• Date: Tue, 15 Sep 2026 03:38:28 GMT
• Title: FRPSS: Feature Rearrangement in Pre-Shape Space for Single-Image Generation
• Abstract summary: Generative models trained on a single image often struggle to balance global structural integrity and local diversity.<n>Existing single-image generation methods rely on random noise to drive the generation process.<n> Feature Rearrangement in Pre-Shape Space for Single-Image Generation (FRPSS) is proposed in this paper.
• Score: 6.313546084738062
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs [14.024934760886298]
  We propose a self-supervised pretraining framework for learning sub-surface scattering (SSS) light transport representations from minimal input.<n>Our method leverages a stereo projector-camera setup that captures only eight high-frequency phase-shift profilometry (PSP) images per view.<n>We introduce a tailored augmentation strategy for PSP-based SSS data, and show that it significantly outperforms standard ImageNet-style augmentations for SSL pretraining.
  arXiv  Detail & Related papers  (2026-06-28T15:32:40Z)
• PSP: Harnessing Position and Shape Priors for Cross-Domain Few-Shot Medical Image Segmentation [12.86282390925016]
  Few-Shot Medical Image (FSMIS) offers a powerful solution to data scarcity but struggles to generalize across different imaging modalities.<n>This performance collapse stems primarily from the drastic texture discrepancies between domains, which mislead models trained on source-specific intensity distributions.<n>We propose a novel framework that harnesses Position and Shape Priors (PSP) for cross-domain FSMIS.
  arXiv  Detail & Related papers  (2026-06-27T08:10:12Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentation [23.546777614096424]
  Few-shot segmentation (FSS) has gained significant attention for its ability to generalize to novel classes with limited supervision.<n>This paper tackles these challenges by introducing VINE, a unified framework that models structural consistency and discrimination to refine class-specific prototypes.
  arXiv  Detail & Related papers  (2026-03-06T06:36:42Z)
• NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation [88.09231548061295]
  Phase-Preserving Diffusion -PD is a model-agnostic reformulation of the diffusion process.<n>-PD preserves input phase while randomizing magnitude, enabling structure-aligned generation without architectural changes.<n>-PD adds no inference-time cost and is compatible with any diffusion model for images or videos.
  arXiv  Detail & Related papers  (2025-12-04T18:59:18Z)
• Hierarchical Spatial-Frequency Aggregation for Spectral Deconvolution Imaging [19.898033482653464]
  In this paper, we introduce a new CSI method to achieve high-fidelity compact matrix design.<n>To tackle the inherent data-dependent operators in SDI, we introduce a Hierarchical Spatial-Spectral Aggregation Unfolding Framework (HSFAUF)<n> Furthermore, to integrate spatial-spectral priors during iterative refinement, we propose a Spatial-Frequency Aggregation Transformer (SFAT)
  arXiv  Detail & Related papers  (2025-11-10T06:29:34Z)
• Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes [60.92139345612904]
  We present Light-SQ, a novel superquadric-based optimization framework.<n>We propose a block-regrow-fill strategy guided by structure-aware volumetric decomposition.<n>Experiments demonstrate that Light-SQ enables efficient, high-fidelity, and editable shape abstraction with superquadrics.
  arXiv  Detail & Related papers  (2025-09-29T16:18:32Z)
• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• Feature Alignment with Equivariant Convolutions for Burst Image Super-Resolution [52.55429225242423]
  We propose a novel framework for Burst Image Super-Resolution (BISR), featuring an equivariant convolution-based alignment.<n>This enables the alignment transformation to be learned via explicit supervision in the image domain and easily applied in the feature domain.<n>Experiments on BISR benchmarks show the superior performance of our approach in both quantitative metrics and visual quality.
  arXiv  Detail & Related papers  (2025-03-11T11:13:10Z)
• Self-supervised Correlation Mining Network for Person Image Generation [9.505343361614928]
  Person image generation aims to perform non-rigid deformation on source images. We propose a Self-supervised Correlation Mining Network (SCM-Net) to rearrange the source images in the feature space. For improving the fidelity of cross-scale pose transformation, we propose a graph based Body Structure Retaining Loss.
  arXiv  Detail & Related papers  (2021-11-26T03:57:46Z)
• Kullback-Leibler Divergence-Based Fuzzy $C$-Means Clustering Incorporating Morphological Reconstruction and Wavelet Frames for Image Segmentation [152.609322951917]
  We come up with a Kullback-Leibler (KL) divergence-based Fuzzy C-Means (FCM) algorithm by incorporating a tight wavelet frame transform and a morphological reconstruction operation. The proposed algorithm works well and comes with better segmentation performance than other comparative algorithms.
  arXiv  Detail & Related papers  (2020-02-21T05:19:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.