Cross-modal retrieval is essential for interpreting cultural heritage data, but its effectiveness is often limited by incomplete or inconsistent textual descriptions, caused by historical data loss and the high cost of expert annotation.While large language models (LLMs) offer a promising solution by enriching textual descriptions, their outputs frequently suffer from hallucinations or miss visually grounded details.To address these challenges, we propose C 3 , a data augmentation framework that enhances cross-modal retrieval performance by improving the completeness and consistency of LLM-generated descriptions.C 3 introduces a completeness evaluation module to assess semantic coverage using both visual cues and language-model outputs.Furthermore, to mitigate factual inconsistencies, we formulate a Markov Decision Process to supervise Chain-of-Thought reasoning, guiding consistency evaluation through adaptive query control.Experiments on the cultural heritage datasets CulTi and TimeTravel, as well as on general benchmarks MSCOCO and Flickr30K, demonstrate that C 3 achieves state-of-the-art performance in both fine-tuned and zero-shot settings.The code of this paper is available at https://github.com/JianZhang24/C-3.

Diffusion-based garment synthesis tasks primarily focus on the design phase in the fashion domain, while the garment production process remains largely underexplored. To bridge this gap, we introduce a new task: Flat Sketch to Realistic Garment Image (FS2RG), which generates realistic garment images by integrating flat sketches and textual guidance. FS2RG presents two key challenges: 1) fabric characteristics are solely guided by textual prompts, providing insufficient visual supervision for diffusion-based models, which limits their ability to capture fine-grained fabric details; 2) flat sketches and textual guidance may provide conflicting information, requiring the model to selectively preserve or modify garment attributes while maintaining structural coherence. To tackle this task, we propose HiGarment, a novel framework that comprises two core components: i) a multi-modal semantic enhancement mechanism that enhances fabric representation across textual and visual modalities, and ii) a harmonized cross-attention mechanism that dynamically balances information from flat sketches and text prompts, allowing controllable synthesis by generating either sketch-aligned (image-biased) or text-guided (text-biased) outputs. Furthermore, we collect Multi-modal Detailed Garment, the largest open-source dataset for garment generation. Experimental results and user studies demonstrate the effectiveness of HiGarment in garment synthesis. The code and dataset are available at https://github.com/Maple498/HiGarment.

Instruction-based garment editing enables precise image modifications via natural language, with broad applications in fashion design and customization. Unlike general editing tasks, it requires understanding garment-specific semantics and attribute dependencies. However, progress is limited by the scarcity of high-quality instruction-image pairs, as manual annotation is costly and hard to scale. While MLLMs have shown promise in automated data synthesis, their application to garment editing is constrained by imprecise instruction modeling and a lack of fashion-specific supervisory signals. To address these challenges, we present an automated pipeline for constructing a garment editing dataset. We first define six editing instruction categories aligned with real-world fashion workflows to guide the generation of balanced and diverse instruction-image triplets. Second, we introduce Fashion Edit Score, a semantic-aware evaluation metric that captures semantic dependencies between garment attributes and provides reliable supervision during construction. Using this pipeline, we construct a total of 52,257 candidate triplets and retain 20,596 high-quality triplets to build EditGarment, the first instruction-based dataset tailored to standalone garment editing. The project page is https://yindq99.github.io/EditGarment-project/.

ABSTRACT In recent years, image restoration has witnessed remarkable advancements. However, reconstructing visually plausible textures while preserving global structural coherence remains a persistent challenge. Existing convolutional neural network (CNN)‐based approaches are inherently limited by their local receptive fields, often struggling to capture global structure. Previously proposed methods mostly focus on structural priors to address the limitation of CNN's receptive field, but we believe that texture priors are also critical factors that influence the quality of image inpainting. To tackle semantic inconsistency and texture blurriness in current methods, we introduce a novel multi‐stage restoration framework. Specifically, our architecture incorporates a dual‐stream U‐Net with attention mechanisms to extract multi‐scale features. The mixed attention‐gated feature fusion module exchanges and combines structure and texture features to generate multi‐scale fused feature maps, which are progressively merged into the decoder to guide the Transformer to generate more realistic images. Additionally, we propose a feature selection feedforward network to replace traditional MLPs in Transformer blocks for adaptive feature refinement. Extensive experiments on CelebA‐HQ and Paris StreetView datasets demonstrate superior performance both qualitatively and quantitatively compared to state‐of‐the‐art methods.

ABSTRACT Arbitrary style transfer, a highly flexible technique with broad application potential, has gained significant attention recently. However, effectively disentangling content and style to synthesize novel stylized images remains a major challenge in arbitrary style transfer tasks. Existing methods primarily perform content and style disentanglement in either a single spatial domain or the frequency domain. We propose a style transfer method based on frequency‐matching and spatial attention called FMSA. FMSA consists of two components: frequency feature matching (FFM) and adaptive spatial attention (ASA). In the spatial domain, an attention mechanism is employed to learn attention scores from the content and style feature maps. These scores are then used to perform point‐wise normalization, generating synthesized features. In the frequency domain, filters are first applied to process the content and style features. The style‐transferred features are subsequently aligned with the magnitude of the style features and the phase of the content features, thereby achieving content‐style disentanglement and reconstruction. We introduce a frequency domain loss to reinforce content consistency in the stylized image while effectively transferring the style patterns to improve image synthesis quality. In addition, we design a decoder based on fast fourier convolution (FFC) that can efficiently decode both global and local information to produce the output. Extensive quantitative and qualitative experiments have demonstrated that the proposed method exhibits superior performance in style transfer tasks, generating results with enhanced stylistic patterns and visual quality. Project page: https://github.com/crFlower/FMSA