Style_Transfer
-
RegionRoute: Regional Style Transfer with Diffusion Model
2026-02-22 16:11:07Bowen Chen, Jake Zuena, Alan C. Bovik, Divya KothandaramanAbstract
Precise spatial control in diffusion-based style transfer remains challenging. This challenge arises because diffusion models treat style as a global feature and lack explicit spatial grounding of style representations, making it difficult to restrict style application to specific objects or regions. To our knowledge, existing diffusion models are unable to perform true localized style transfer, typically relying on handcrafted masks or multi-stage post-processing that introduce boundary artifacts and limit generalization. To address this, we propose an attention-supervised diffusion framework that explicitly teaches the model where to apply a given style by aligning the attention scores of style tokens with object masks during training. Two complementary objectives, a Focus loss based on KL divergence and a Cover loss using binary cross-entropy, jointly encourage accurate localization and dense coverage. A modular LoRA-MoE design further enables efficient and scalable multi-style adaptation. To evaluate localized stylization, we introduce the Regional Style Editing Score, which measures Regional Style Matching through CLIP-based similarity within the target region and Identity Preservation via masked LPIPS and pixel-level consistency on unedited areas. Experiments show that our method achieves mask-free, single-object style transfer at inference, producing regionally accurate and visually coherent results that outperform existing diffusion-based editing approaches.
Abstract (translated)
在基于扩散的风格迁移中，实现精确的空间控制仍然是一项挑战。这一难题产生的原因是扩散模型将风格视为全局特征，并且缺乏对风格表示的具体空间定位，这使得限制特定对象或区域内的风格应用变得困难。据我们所知，现有的扩散模型无法执行真正的局部化风格传输，通常依赖于手工设计的掩码或多阶段后处理技术，这些方法会产生边界伪影并限制了泛化能力。 为了解决这个问题，我们提出了一种基于注意力监督的扩散框架。通过在训练过程中将风格标记的注意力分数与对象掩码对齐的方式，该框架明确地教导模型如何应用给定的风格。两个互补的目标——基于KL散度的Focus损失和使用二元交叉熵的Cover损失共同鼓励准确的空间定位和密集覆盖。此外，一个模块化的LoRA-MoE设计进一步实现了高效的多风格适应。 为了评估局部化样式化的效果，我们引入了“区域风格编辑评分”（Regional Style Editing Score），它通过目标区域内的CLIP基相似性测量区域风格匹配，并通过掩码LPIPS和未编辑区域的像素级一致性来衡量身份保持。实验结果表明，我们的方法能够在推理时实现无掩码、单对象的风格转换，生成准确且视觉上一致的结果，优于现有的基于扩散的方法。
URL
https://arxiv.org/abs/2602.19254
PDF
-
Structure-Level Disentangled Diffusion for Few-Shot Chinese Font Generation
2026-02-21 15:41:06Jie Li, Suorong Yang, Jian Zhao, Furao ShenAbstract
Few-shot Chinese font generation aims to synthesize new characters in a target style using only a handful of reference images. Achieving accurate content rendering and faithful style transfer requires effective disentanglement between content and style. However, existing approaches achieve only feature-level disentanglement, allowing the generator to re-entangle these features, leading to content distortion and degraded style fidelity. We propose the Structure-Level Disentangled Diffusion Model (SLD-Font), which receives content and style information from two separate channels. SimSun-style images are used as content templates and concatenated with noisy latent features as the input. Style features extracted by a CLIP model from target-style images are integrated via cross-attention. Additionally, we train a Background Noise Removal module in the pixel space to remove background noise in complex stroke regions. Based on theoretical validation of disentanglement effectiveness, we introduce a parameter-efficient fine-tuning strategy that updates only the style-related modules. This allows the model to better adapt to new styles while avoiding overfitting to the reference images' content. We further introduce the Grey and OCR metrics to evaluate the content quality of generated characters. Experimental results show that SLD-Font achieves significantly higher style fidelity while maintaining comparable content accuracy to existing state-of-the-art methods.
Abstract (translated)
少量样本中文字体生成的目标是使用少量参考图像来合成目标风格下的新字符。为了实现准确的内容呈现和忠实的风格转换，需要在内容与风格之间进行有效的解耦合。然而，现有的方法仅实现了特征级别的解耦合，这允许生成器重新结合这些特征，导致内容扭曲和风格保真度降低。我们提出了结构级解耦扩散模型（SLD-Font），该模型从两个独立的通道接收内容和风格信息。使用SimSun样式的图像作为内容模板，并将其与噪声潜在特性拼接在一起作为输入。通过跨注意力机制将CLIP模型从目标风格图像中提取的风格特征集成进来。此外，我们训练了一个背景噪声移除模块，在像素空间内删除复杂笔画区域中的背景噪声。基于对解耦有效性理论验证的基础上，我们引入了一种参数高效的微调策略，该策略仅更新与风格相关的模块，这使模型能够更好地适应新风格，同时避免过度拟合参考图像的内容。进一步地，我们引入了Grey和OCR指标来评估生成字符的内容质量。实验结果显示，SLD-Font在保持现有最先进的方法相当的内容准确度的同时，实现了显著更高的风格保真度。
URL
https://arxiv.org/abs/2602.18874
PDF
-
StereoAdapter-2: Globally Structure-Consistent Underwater Stereo Depth Estimation
2026-02-18 22:12:08Zeyu Ren, Xiang Li, Yiran Wang, Zeyu Zhang, Hao TangAbstract
Stereo depth estimation is fundamental to underwater robotic perception, yet suffers from severe domain shifts caused by wavelength-dependent light attenuation, scattering, and refraction. Recent approaches leverage monocular foundation models with GRU-based iterative refinement for underwater adaptation; however, the sequential gating and local convolutional kernels in GRUs necessitate multiple iterations for long-range disparity propagation, limiting performance in large-disparity and textureless underwater regions. In this paper, we propose StereoAdapter-2, which replaces the conventional ConvGRU updater with a novel ConvSS2D operator based on selective state space models. The proposed operator employs a four-directional scanning strategy that naturally aligns with epipolar geometry while capturing vertical structural consistency, enabling efficient long-range spatial propagation within a single update step at linear computational complexity. Furthermore, we construct UW-StereoDepth-80K, a large-scale synthetic underwater stereo dataset featuring diverse baselines, attenuation coefficients, and scattering parameters through a two-stage generative pipeline combining semantic-aware style transfer and geometry-consistent novel view synthesis. Combined with dynamic LoRA adaptation inherited from StereoAdapter, our framework achieves state-of-the-art zero-shot performance on underwater benchmarks with 17% improvement on TartanAir-UW and 7.2% improvment on SQUID, with real-world validation on the BlueROV2 platform demonstrates the robustness of our approach. Code: this https URL. Website: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2602.16915
PDF
-
Surgical Activation Steering via Generative Causal Mediation
2026-02-17 23:13:18Aruna Sankaranarayanan, Amir Zur, Atticus Geiger, Dylan Hadfield-MenellAbstract
Where should we intervene in a language model (LM) to control behaviors that are diffused across many tokens of a long-form response? We introduce Generative Causal Mediation (GCM), a procedure for selecting model components, e.g., attention heads, to steer a binary concept (e.g., talk in verse vs. talk in prose) from contrastive long-form responses. In GCM, we first construct a dataset of contrasting inputs and responses. Then, we quantify how individual model components mediate the contrastive concept and select the strongest mediators for steering. We evaluate GCM on three tasks--refusal, sycophancy, and style transfer--across three language models. GCM successfully localizes concepts expressed in long-form responses and consistently outperforms correlational probe-based baselines when steering with a sparse set of attention heads. Together, these results demonstrate that GCM provides an effective approach for localizing and controlling the long-form responses of LMs.
Abstract (translated)
URL
https://arxiv.org/abs/2602.16080
PDF
-
Text Style Transfer with Parameter-efficient LLM Finetuning and Round-trip Translation
2026-02-16 18:52:43Ruoxi Liu, Philipp KoehnAbstract
This paper proposes a novel method for Text Style Transfer (TST) based on parameter-efficient fine-tuning of Large Language Models (LLMs). Addressing the scarcity of parallel corpora that map between styles, the study employs roundtrip translation to synthesize such parallel datasets from monolingual corpora. This approach creates 'neutralized' text devoid of stylistic attributes, essentially creating a shared input style at training-time and inference-time. Experimental results demonstrate consistent superiority of this method over zero-shot prompting and fewshot ICL techniques measured by BLEU scores and style accuracy scores across four investigated domains. Furthermore, the integration of retrieval-augmented generation (RAG) for terminology and name knowledge enhances robustness and stylistic consistency.
Abstract (translated)
URL
https://arxiv.org/abs/2602.15013
PDF
-
CoCoDiff: Correspondence-Consistent Diffusion Model for Fine-grained Style Transfer
2026-02-16 04:52:29Wenbo Nie, Zixiang Li, Renshuai Tao, Bin Wu, Yunchao Wei, Yao ZhaoAbstract
Transferring visual style between images while preserving semantic correspondence between similar objects remains a central challenge in computer vision. While existing methods have made great strides, most of them operate at global level but overlook region-wise and even pixel-wise semantic correspondence. To address this, we propose CoCoDiff, a novel training-free and low-cost style transfer framework that leverages pretrained latent diffusion models to achieve fine-grained, semantically consistent stylization. We identify that correspondence cues within generative diffusion models are under-explored and that content consistency across semantically matched regions is often neglected. CoCoDiff introduces a pixel-wise semantic correspondence module that mines intermediate diffusion features to construct a dense alignment map between content and style images. Furthermore, a cycle-consistency module then enforces structural and perceptual alignment across iterations, yielding object and region level stylization that preserves geometry and detail. Despite requiring no additional training or supervision, CoCoDiff delivers state-of-the-art visual quality and strong quantitative results, outperforming methods that rely on extra training or annotations.
Abstract (translated)
URL
https://arxiv.org/abs/2602.14464
PDF
-
Diverging Flows: Detecting Extrapolations in Conditional Generation
2026-02-13 16:15:58Constantinos Tsakonas, Serena Ivaldi, Jean-Baptiste MouretAbstract
The ability of Flow Matching (FM) to model complex conditional distributions has established it as the state-of-the-art for prediction tasks (e.g., robotics, weather forecasting). However, deployment in safety-critical settings is hindered by a critical extrapolation hazard: driven by smoothness biases, flow models yield plausible outputs even for off-manifold conditions, resulting in silent failures indistinguishable from valid predictions. In this work, we introduce Diverging Flows, a novel approach that enables a single model to simultaneously perform conditional generation and native extrapolation detection by structurally enforcing inefficient transport for off-manifold inputs. We evaluate our method on synthetic manifolds, cross-domain style transfer, and weather temperature forecasting, demonstrating that it achieves effective detection of extrapolations without compromising predictive fidelity or inference latency. These results establish Diverging Flows as a robust solution for trustworthy flow models, paving the way for reliable deployment in domains such as medicine, robotics, and climate science.
Abstract (translated)
URL
https://arxiv.org/abs/2602.13061
PDF
-
The Constant Eye: Benchmarking and Bridging Appearance Robustness in Autonomous Driving
2026-02-13 03:22:00Jiabao Wang, Hongyu Zhou, Yuanbo Yang, Jiahao Shao, Yiyi LiaoAbstract
Despite rapid progress, autonomous driving algorithms remain notoriously fragile under Out-of-Distribution (OOD) conditions. We identify a critical decoupling failure in current research: the lack of distinction between appearance-based shifts, such as weather and lighting, and structural scene changes. This leaves a fundamental question unanswered: Is the planner failing because of complex road geometry, or simply because it is raining? To resolve this, we establish navdream, a high-fidelity robustness benchmark leveraging generative pixel-aligned style transfer. By creating a visual stress test with negligible geometric deviation, we isolate the impact of appearance on driving performance. Our evaluation reveals that existing planning algorithms often show significant degradation under OOD appearance conditions, even when the underlying scene structure remains consistent. To bridge this gap, we propose a universal perception interface leveraging a frozen visual foundation model (DINOv3). By extracting appearance-invariant features as a stable interface for the planner, we achieve exceptional zero-shot generalization across diverse planning paradigms, including regression-based, diffusion-based, and scoring-based models. Our plug-and-play solution maintains consistent performance across extreme appearance shifts without requiring further fine-tuning. The benchmark and code will be made available.
Abstract (translated)
URL
https://arxiv.org/abs/2602.12563
PDF
-
Speech to Speech Synthesis for Voice Impersonation
2026-02-13 01:22:25Bjorn Johnson, Jared LevyAbstract
Numerous models have shown great success in the fields of speech recognition as well as speech synthesis, but models for speech to speech processing have not been heavily explored. We propose Speech to Speech Synthesis Network (STSSN), a model based on current state of the art systems that fuses the two disciplines in order to perform effective speech to speech style transfer for the purpose of voice impersonation. We show that our proposed model is quite powerful, and succeeds in generating realistic audio samples despite a number of drawbacks in its capacity. We benchmark our proposed model by comparing it with a generative adversarial model which accomplishes a similar task, and show that ours produces more convincing results.
Abstract (translated)
URL
https://arxiv.org/abs/2602.16721
PDF
-
RFDM: Residual Flow Diffusion Model for Efficient Causal Video Editing
2026-02-06 16:56:30Mohammadreza Salehi, Mehdi Noroozi, Luca Morreale, Ruchika Chavhan, Malcolm Chadwick, Alberto Gil Ramos, Abhinav MehrotraAbstract
Instructional video editing applies edits to an input video using only text prompts, enabling intuitive natural-language control. Despite rapid progress, most methods still require fixed-length inputs and substantial compute. Meanwhile, autoregressive video generation enables efficient variable-length synthesis, yet remains under-explored for video editing. We introduce a causal, efficient video editing model that edits variable-length videos frame by frame. For efficiency, we start from a 2D image-to-image (I2I) diffusion model and adapt it to video-to-video (V2V) editing by conditioning the edit at time step t on the model's prediction at t-1. To leverage videos' temporal redundancy, we propose a new I2I diffusion forward process formulation that encourages the model to predict the residual between the target output and the previous prediction. We call this Residual Flow Diffusion Model (RFDM), which focuses the denoising process on changes between consecutive frames. Moreover, we propose a new benchmark that better ranks state-of-the-art methods for editing tasks. Trained on paired video data for global/local style transfer and object removal, RFDM surpasses I2I-based methods and competes with fully spatiotemporal (3D) V2V models, while matching the compute of image models and scaling independently of input video length. More content can be found in: this https URL
Abstract (translated)
该段落介绍了一种新的视频编辑方法，名为Residual Flow Diffusion Model（RFDM）。这种方法旨在通过文本指令来编辑输入视频，并且是基于因果关系的高效模型。与传统方法不同的是，它能够处理任意长度的视频数据，同时保持计算资源的要求较低。 具体来说，该方法从二维图像到图像（I2I）扩散模型开始，然后将其转换为适用于视频到视频（V2V）编辑的模型。在这一过程中，模型会在时间步骤t使用前一时刻t-1的预测来调整编辑操作。为了更好地利用视频中的时间冗余性，研究人员提出了一种新的I2I扩散过程公式，该公式鼓励模型预测目标输出与之前预测之间的残差（即差异）。这种设计使得RFDM更加专注于连续帧间的变化。 除此之外，研究团队还提出了一个新的基准测试方法，用于更准确地评估各种视频编辑技术的效果。通过训练具有全局/局部风格转换和对象移除功能的配对视频数据集，RFDM在性能上超越了传统的I2I模型，并且可以与全时空（3D）V2V模型相媲美，同时保持计算成本与图像处理模型相当，并独立于输入视频长度进行扩展。 总体而言，这种方法通过创新地结合时间序列预测和差分编辑策略，为高效的视频编辑任务提供了一个新的方向。更多信息可以在提供的链接中找到。
URL
https://arxiv.org/abs/2602.06871
PDF
-
WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark
2026-02-06 13:42:30Wang Lin, Feng Wang, Majun Zhang, Wentao Hu, Tao Jin, Zhou Zhao, Fei Wu, Jingyuan Chen, Alan Yuille, Sucheng RenAbstract
Recent advances in image editing models have demonstrated remarkable capabilities in executing explicit instructions, such as attribute manipulation, style transfer, and pose synthesis. However, these models often face challenges when dealing with implicit editing instructions, which describe the cause of a visual change without explicitly detailing the resulting outcome. These limitations arise because existing models rely on uniform editing strategies that are not equipped to handle the complex world knowledge and reasoning required for implicit instructions. To address this gap, we introduce \textbf{WorldEdit}, a dataset specifically designed to enable world-driven image editing. WorldEdit consists of high-quality editing samples, guided by paraphrased instructions that align with real-world causal logic. Furthermore, we provide \textbf{WorldEdit-Test} for evaluating the existing model's performance on causal editing scenarios. With WorldEdit, we use a two-stage training framework for fine-tuning models like Bagel, integrating with a causal verification reward. Our results show that the proposed dataset and methods significantly narrow the gap with GPT-4o and Nano-Banana, demonstrating competitive performance not only in instruction following but also in knowledge plausibility, where many open-source systems typically struggle.
Abstract (translated)
最近在图像编辑模型方面取得的进展展示了执行显式指令（如属性操控、风格转换和姿态合成）的非凡能力。然而，当面对隐含编辑指令时，这些模型往往会遇到挑战。隐含编辑指令描述的是视觉变化的原因而非详细的结果。现有模型面临的限制在于它们依赖于统一的编辑策略，无法处理实现隐含指令所需的复杂世界知识和推理过程。 为了解决这一差距，我们引入了\textbf{WorldEdit}，这是一个专门设计用于支持以世界驱动方式进行图像编辑的数据集。WorldEdit包括了大量的高质量编辑样本，并通过与现实世界的因果逻辑一致的语句指导这些样本的生成。此外，为了评估现有模型在处理因果编辑场景中的表现，我们还提供了名为\textbf{WorldEdit-Test}的测试数据集。 使用WorldEdit，我们提出了一种两阶段训练框架来对Bagel等模型进行微调，并结合了因果验证奖励机制。我们的实验结果表明，通过所提出的这一新数据集和方法，在遵循指令和知识合理性方面（这通常困扰着许多开源系统），与GPT-4o和Nano-Banana相比，差距显著缩小，展示了相当的性能水平。 这段翻译概述了一种新的图像编辑模型训练方式，并强调了它在处理因果性较强的隐含编辑任务时所取得的进步。
URL
https://arxiv.org/abs/2602.07095
PDF
-
Untwisting RoPE: Frequency Control for Shared Attention in DiTs
2026-02-04 20:01:59Aryan Mikaeili, Or Patashnik, Andrea Tagliasacchi, Daniel Cohen-Or, Ali Mahdavi-AmiriAbstract
Positional encodings are essential to transformer-based generative models, yet their behavior in multimodal and attention-sharing settings is not fully understood. In this work, we present a principled analysis of Rotary Positional Embeddings (RoPE), showing that RoPE naturally decomposes into frequency components with distinct positional sensitivities. We demonstrate that this frequency structure explains why shared-attention mechanisms, where a target image is generated while attending to tokens from a reference image, can lead to reference copying, in which the model reproduces content from the reference instead of extracting only its stylistic cues. Our analysis reveals that the high-frequency components of RoPE dominate the attention computation, forcing queries to attend mainly to spatially aligned reference tokens and thereby inducing this unintended copying behavior. Building on these insights, we introduce a method for selectively modulating RoPE frequency bands so that attention reflects semantic similarity rather than strict positional alignment. Applied to modern transformer-based diffusion architectures, where all tokens share attention, this modulation restores stable and meaningful shared attention. As a result, it enables effective control over the degree of style transfer versus content copying, yielding a proper style-aligned generation process in which stylistic attributes are transferred without duplicating reference content.
Abstract (translated)
位置编码是基于变压器的生成模型中的关键组成部分，然而，在多模态和注意力共享设置下的行为尚未完全理解。在本文中，我们对旋转位置嵌入（RoPE）进行了系统的分析，揭示了RoPE自然地分解成具有不同位置敏感性的频率分量。我们展示了这种频率结构能够解释为什么共用注意力机制——即在关注参考图像中的标记时生成目标图像——会导致复制参考内容的行为，而不是仅仅提取其风格提示。 我们的分析发现，RoPE的高频部分在注意力计算中占主导地位，迫使查询主要关注空间对齐的参考标记，从而导致这种意外的复制行为。基于这些见解，我们提出了一种方法来选择性地调节RoPE频率带，使得注意力反映的是语义相似性而不是严格的位置对齐。当应用于现代基于变压器的扩散架构中所有令牌共用注意力的情况下时，这种调制恢复了稳定且有意义的共享注意力。因此，它能够有效地控制风格转移的程度与内容复制之间的平衡，在此过程中传递风格属性而不重复参考内容，从而实现正确的风格一致生成过程。 这段翻译详细阐述了RoPE在多模态和共享注意力机制中的行为，并提出了一种调节方法以改善模型性能，使之更适于有效的样式迁移而非内容复制。
URL
https://arxiv.org/abs/2602.05013
PDF
-
Multi-Objective Optimization for Synthetic-to-Real Style Transfer
2026-02-03 15:14:23Estelle Chigot, Thomas Oberlin, Manon Huguenin, Dennis WilsonAbstract
Semantic segmentation networks require large amounts of pixel-level annotated data, which are costly to obtain for real-world images. Computer graphics engines can generate synthetic images alongside their ground-truth annotations. However, models trained on such images can perform poorly on real images due to the domain gap between real and synthetic images. Style transfer methods can reduce this difference by applying a realistic style to synthetic images. Choosing effective data transformations and their sequence is difficult due to the large combinatorial search space of style transfer operators. Using multi-objective genetic algorithms, we optimize pipelines to balance structural coherence and style similarity to target domains. We study the use of paired-image metrics on individual image samples during evolution to enable rapid pipeline evaluation, as opposed to standard distributional metrics that require the generation of many images. After optimization, we evaluate the resulting Pareto front using distributional metrics and segmentation performance. We apply this approach to standard datasets in synthetic-to-real domain adaptation: from the video game GTA5 to real image datasets Cityscapes and ACDC, focusing on adverse conditions. Results demonstrate that evolutionary algorithms can propose diverse augmentation pipelines adapted to different objectives. The contribution of this work is the formulation of style transfer as a sequencing problem suitable for evolutionary optimization and the study of efficient metrics that enable feasible search in this space. The source code is available at: this https URL.
Abstract (translated)
语义分割网络需要大量的像素级标注数据，这些数据在获取真实世界的图像时成本高昂。计算机图形引擎可以生成合成图像及其地面实况注释。然而，在这类图像上进行训练的模型可能在真实图像上的表现不佳，因为真实图像和合成图像之间存在领域差距。通过将现实风格应用于合成图像，风格迁移方法可以减少这种差异。但由于风格转换操作的组合搜索空间很大，选择有效的数据变换及其顺序是很困难的。 我们使用多目标遗传算法来优化管道，以便在结构一致性和与目标领域的样式相似性之间取得平衡。我们在进化过程中研究了对单个图像样本使用配对图像度量的方法，以实现快速的流水线评估，而不是需要生成许多图像的标准分布度量。优化后，我们使用分布度量和分割性能来评估所得的帕累托前沿。 我们将这种方法应用于从视频游戏GTA5到真实图像数据集Cityscapes和ACDC（假设是某个特定数据集）的合成到现实领域适应的标准数据集中，重点在于不利条件。结果表明，进化算法可以提出适合不同目标的各种增强管道。 这项工作的贡献在于将风格迁移表述为一个适用于进化优化的序列问题，并研究了在这一空间中进行可行搜索的有效度量。源代码可在以下网址获得：this https URL.
URL
https://arxiv.org/abs/2602.03625
PDF
-
VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations
2026-02-02 16:58:17Fatemeh Zargarbashi, Dhruv Agrawal, Jakob Buhmann, Martin Guay, Stelian Coros, Robert W. SumnerAbstract
Human motion data is inherently rich and complex, containing both semantic content and subtle stylistic features that are challenging to model. We propose a novel method for effective disentanglement of the style and content in human motion data to facilitate style transfer. Our approach is guided by the insight that content corresponds to coarse motion attributes while style captures the finer, expressive details. To model this hierarchy, we employ Residual Vector Quantized Variational Autoencoders (RVQ-VAEs) to learn a coarse-to-fine representation of motion. We further enhance the disentanglement by integrating contrastive learning and a novel information leakage loss with codebook learning to organize the content and the style across different codebooks. We harness this disentangled representation using our simple and effective inference-time technique Quantized Code Swapping, which enables motion style transfer without requiring any fine-tuning for unseen styles. Our framework demonstrates strong versatility across multiple inference applications, including style transfer, style removal, and motion blending.
Abstract (translated)
URL
https://arxiv.org/abs/2602.02334
PDF
-
Tune-Your-Style: Intensity-tunable 3D Style Transfer with Gaussian Splatting
2026-01-31 09:17:26Yian Zhao, Rushi Ye, Ruochong Zheng, Zesen Cheng, Chaoran Feng, Jiashu Yang, Pengchong Qiao, Chang Liu, Jie ChenAbstract
3D style transfer refers to the artistic stylization of 3D assets based on reference style images. Recently, 3DGS-based stylization methods have drawn considerable attention, primarily due to their markedly enhanced training and rendering speeds. However, a vital challenge for 3D style transfer is to strike a balance between the content and the patterns and colors of the style. Although the existing methods strive to achieve relatively balanced outcomes, the fixed-output paradigm struggles to adapt to the diverse content-style balance requirements from different users. In this work, we introduce a creative intensity-tunable 3D style transfer paradigm, dubbed \textbf{Tune-Your-Style}, which allows users to flexibly adjust the style intensity injected into the scene to match their desired content-style balance, thus enhancing the customizability of 3D style transfer. To achieve this goal, we first introduce Gaussian neurons to explicitly model the style intensity and parameterize a learnable style tuner to achieve intensity-tunable style injection. To facilitate the learning of tunable stylization, we further propose the tunable stylization guidance, which obtains multi-view consistent stylized views from diffusion models through cross-view style alignment, and then employs a two-stage optimization strategy to provide stable and efficient guidance by modulating the balance between full-style guidance from the stylized views and zero-style guidance from the initial rendering. Extensive experiments demonstrate that our method not only delivers visually appealing results, but also exhibits flexible customizability for 3D style transfer. Project page is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2602.00618
PDF
-
End-to-end example-based sim-to-real RL policy transfer based on neural stylisation with application to robotic cutting
2026-01-28 18:45:55Jamie Hathaway, Alireza Rastegarpanah, Rustam StolkinAbstract
Whereas reinforcement learning has been applied with success to a range of robotic control problems in complex, uncertain environments, reliance on extensive data - typically sourced from simulation environments - limits real-world deployment due to the domain gap between simulated and physical systems, coupled with limited real-world sample availability. We propose a novel method for sim-to-real transfer of reinforcement learning policies, based on a reinterpretation of neural style transfer from image processing to synthesise novel training data from unpaired unlabelled real world datasets. We employ a variational autoencoder to jointly learn self-supervised feature representations for style transfer and generate weakly paired source-target trajectories to improve physical realism of synthesised trajectories. We demonstrate the application of our approach based on the case study of robot cutting of unknown materials. Compared to baseline methods, including our previous work, CycleGAN, and conditional variational autoencoder-based time series translation, our approach achieves improved task completion time and behavioural stability with minimal real-world data. Our framework demonstrates robustness to geometric and material variation, and highlights the feasibility of policy adaptation in challenging contact-rich tasks where real-world reward information is unavailable.
Abstract (translated)
URL
https://arxiv.org/abs/2601.20846
PDF
-
TeleStyle: Content-Preserving Style Transfer in Images and Videos
2026-01-28 02:16:03Shiwen Zhang, Xiaoyan Yang, Bojia Zi, Haibin Huang, Chi Zhang, Xuelong LiAbstract
Content-preserving style transfer, generating stylized outputs based on content and style references, remains a significant challenge for Diffusion Transformers (DiTs) due to the inherent entanglement of content and style features in their internal representations. In this technical report, we present TeleStyle, a lightweight yet effective model for both image and video stylization. Built upon Qwen-Image-Edit, TeleStyle leverages the base model's robust capabilities in content preservation and style customization. To facilitate effective training, we curated a high-quality dataset of distinct specific styles and further synthesized triplets using thousands of diverse, in-the-wild style categories. We introduce a Curriculum Continual Learning framework to train TeleStyle on this hybrid dataset of clean (curated) and noisy (synthetic) triplets. This approach enables the model to generalize to unseen styles without compromising precise content fidelity. Additionally, we introduce a video-to-video stylization module to enhance temporal consistency and visual quality. TeleStyle achieves state-of-the-art performance across three core evaluation metrics: style similarity, content consistency, and aesthetic quality. Code and pre-trained models are available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2601.20175
PDF
-
DiffStyle3D: Consistent 3D Gaussian Stylization via Attention Optimization
2026-01-27 15:41:11Yitong Yang, Xuexin Liu, Yinglin Wang, Jing Wang, Hao Dou, Changshuo Wang, Shuting HeAbstract
3D style transfer enables the creation of visually expressive 3D content, enriching the visual appearance of 3D scenes and objects. However, existing VGG- and CLIP-based methods struggle to model multi-view consistency within the model itself, while diffusion-based approaches can capture such consistency but rely on denoising directions, leading to unstable training. To address these limitations, we propose DiffStyle3D, a novel diffusion-based paradigm for 3DGS style transfer that directly optimizes in the latent space. Specifically, we introduce an Attention-Aware Loss that performs style transfer by aligning style features in the self-attention space, while preserving original content through content feature alignment. Inspired by the geometric invariance of 3D stylization, we propose a Geometry-Guided Multi-View Consistency method that integrates geometric information into self-attention to enable cross-view correspondence modeling. Based on geometric information, we additionally construct a geometry-aware mask to prevent redundant optimization in overlapping regions across views, which further improves multi-view consistency. Extensive experiments show that DiffStyle3D outperforms state-of-the-art methods, achieving higher stylization quality and visual realism.
Abstract (translated)
URL
https://arxiv.org/abs/2601.19717
PDF
-
Quran-MD: A Fine-Grained Multilingual Multimodal Dataset of the Quran
2026-01-25 15:23:37Muhammad Umar Salman, Mohammad Areeb Qazi, Mohammed Talha AlamAbstract
We present Quran MD, a comprehensive multimodal dataset of the Quran that integrates textual, linguistic, and audio dimensions at the verse and word levels. For each verse (ayah), the dataset provides its original Arabic text, English translation, and phonetic transliteration. To capture the rich oral tradition of Quranic recitation, we include verse-level audio from 32 distinct reciters, reflecting diverse recitation styles and dialectical nuances. At the word level, each token is paired with its corresponding Arabic script, English translation, transliteration, and an aligned audio recording, allowing fine-grained analysis of pronunciation, phonology, and semantic context. This dataset supports various applications, including natural language processing, speech recognition, text-to-speech synthesis, linguistic analysis, and digital Islamic studies. Bridging text and audio modalities across multiple reciters, this dataset provides a unique resource to advance computational approaches to Quranic recitation and study. Beyond enabling tasks such as ASR, tajweed detection, and Quranic TTS, it lays the foundation for multimodal embeddings, semantic retrieval, style transfer, and personalized tutoring systems that can support both research and community applications. The dataset is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2601.17880
PDF
-
Stylizing ViT: Anatomy-Preserving Instance Style Transfer for Domain Generalization
2026-01-24 20:53:02Sebastian Doerrich, Francesco Di Salvo, Jonas Alle, Christian LedigAbstract
Deep learning models in medical image analysis often struggle with generalizability across domains and demographic groups due to data heterogeneity and scarcity. Traditional augmentation improves robustness, but fails under substantial domain shifts. Recent advances in stylistic augmentation enhance domain generalization by varying image styles but fall short in terms of style diversity or by introducing artifacts into the generated images. To address these limitations, we propose Stylizing ViT, a novel Vision Transformer encoder that utilizes weight-shared attention blocks for both self- and cross-attention. This design allows the same attention block to maintain anatomical consistency through self-attention while performing style transfer via cross-attention. We assess the effectiveness of our method for domain generalization by employing it for data augmentation on three distinct image classification tasks in the context of histopathology and dermatology. Results demonstrate an improved robustness (up to +13% accuracy) over the state of the art while generating perceptually convincing images without artifacts. Additionally, we show that Stylizing ViT is effective beyond training, achieving a 17% performance improvement during inference when used for test-time augmentation. The source code is available at this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2601.17586
PDF
