Zili Yi

Chao Xu, Jiangning Zhang, Miao Hua et al.

This paper presents a novel Region-Aware Face Swapping (RAFSwap) network to achieve identity-consistent harmonious high-resolution face generation in a local-global manner: \textbf{1)} Local Facial Region-Aware (FRA) branch augments local identity-relevant features by introducing the Transformer to effectively model misaligned cross-scale semantic interaction. \textbf{2)} Global Source Feature-Adaptive (SFA) branch further complements global identity-relevant cues for generating identity-consistent swapped faces. Besides, we propose a \textit{Face Mask Predictor} (FMP) module incorporated with StyleGAN2 to predict identity-relevant soft facial masks in an unsupervised manner that is more practical for generating harmonious high-resolution faces. Abundant experiments qualitatively and quantitatively demonstrate the superiority of our method for generating more identity-consistent high-resolution swapped faces over SOTA methods, \eg, obtaining 96.70 ID retrieval that outperforms SOTA MegaFS by 5.87$\uparrow$.

Zihao Wang, Wei Liu, Qian He et al.

Training a text-to-image generator in the general domain (e.g., Dall.e, CogView) requires huge amounts of paired text-image data, which is too expensive to collect. In this paper, we propose a self-supervised scheme named as CLIP-GEN for general text-to-image generation with the language-image priors extracted with a pre-trained CLIP model. In our approach, we only require a set of unlabeled images in the general domain to train a text-to-image generator. Specifically, given an image without text labels, we first extract the embedding of the image in the united language-vision embedding space with the image encoder of CLIP. Next, we convert the image into a sequence of discrete tokens in the VQGAN codebook space (the VQGAN model can be trained with the unlabeled image dataset in hand). Finally, we train an autoregressive transformer that maps the image tokens from its unified language-vision representation. Once trained, the transformer can generate coherent image tokens based on the text embedding extracted from the text encoder of CLIP upon an input text. Such a strategy enables us to train a strong and general text-to-image generator with large text-free image dataset such as ImageNet. Qualitative and quantitative evaluations verify that our method significantly outperforms optimization-based text-to-image methods in terms of image quality while not compromising the text-image matching. Our method can even achieve comparable performance as flagship supervised models like CogView.

Wei Liu, Fangyue Liu, Fei Ding et al.

Generating a new font library is a very labor-intensive and time-consuming job for glyph-rich scripts. Few-shot font generation is thus required, as it requires only a few glyph references without fine-tuning during test. Existing methods follow the style-content disentanglement paradigm and expect novel fonts to be produced by combining the style codes of the reference glyphs and the content representations of the source. However, these few-shot font generation methods either fail to capture content-independent style representations, or employ localized component-wise style representations, which is insufficient to model many Chinese font styles that involve hyper-component features such as inter-component spacing and "connected-stroke". To resolve these drawbacks and make the style representations more reliable, we propose a self-supervised cross-modality pre-training strategy and a cross-modality transformer-based encoder that is conditioned jointly on the glyph image and the corresponding stroke labels. The cross-modality encoder is pre-trained in a self-supervised manner to allow effective capture of cross- and intra-modality correlations, which facilitates the content-style disentanglement and modeling style representations of all scales (stroke-level, component-level and character-level). The pre-trained encoder is then applied to the downstream font generation task without fine-tuning. Experimental comparisons of our method with state-of-the-art methods demonstrate our method successfully transfers styles of all scales. In addition, it only requires one reference glyph and achieves the lowest rate of bad cases in the few-shot font generation task 28% lower than the second best

Bingchuan Li, Tianxiang Ma, Peng Zhang et al.

The StyleGAN family succeed in high-fidelity image generation and allow for flexible and plausible editing of generated images by manipulating the semantic-rich latent style space.However, projecting a real image into its latent space encounters an inherent trade-off between inversion quality and editability. Existing encoder-based or optimization-based StyleGAN inversion methods attempt to mitigate the trade-off but see limited performance. To fundamentally resolve this problem, we propose a novel two-phase framework by designating two separate networks to tackle editing and reconstruction respectively, instead of balancing the two. Specifically, in Phase I, a W-space-oriented StyleGAN inversion network is trained and used to perform image inversion and editing, which assures the editability but sacrifices reconstruction quality. In Phase II, a carefully designed rectifying network is utilized to rectify the inversion errors and perform ideal reconstruction. Experimental results show that our approach yields near-perfect reconstructions without sacrificing the editability, thus allowing accurate manipulation of real images. Further, we evaluate the performance of our rectifying network, and see great generalizability towards unseen manipulation types and out-of-domain images.

Xinyu Chen, Yuyi Qian, Jiang Lin et al.

Video object insertion requires ensuring spatio-temporal coherence and interactive realism, extending far beyond simple content placement. However, current approaches are often hindered by a reliance on explicit motion engineering or resource-intensive retraining, restricting their flexibility and generalization. To bridge this gap, we present \textit{SimInsert}, a training-free paradigm that efficiently decouples the task into intuitive single-frame editing and semantic motion description. By harnessing the robust generative priors of image-to-video diffusion models, SimInsert propagates edits temporally, strictly preserving background invariance while enabling plausible, text-driven interactions between the inserted object and the dynamic environment. Our approach hinges on non-invasive guidance mechanisms that enforce structural consistency, facilitate seamless boundary fusion, and counteract the fidelity drift that typically accumulates during the denoising trajectory. Extensive quantitative experiments validate our efficacy: SimInsert surpasses state-of-the-art methods with an 18.8\% gain in PSNR, 20.1\% in SSIM, and a 44.1\% decrease in LPIPS, offering a streamlined solution for high-fidelity video editing.

Xiaokun Sun, Zhenyu Zhang, Ying Tai et al.

To integrate digital humans into everyday life, there is a strong demand for generating high-quality, fine-grained disentangled 3D avatars that support expressive animation and simulation capabilities, ideally from low-cost textual inputs. Although text-driven 3D avatar generation has made significant progress by leveraging 2D generative priors, existing methods still struggle to fulfill all these requirements simultaneously. To address this challenge, we propose DreamBarbie, a novel text-driven framework for generating animatable 3D avatars with separable shoes, accessories, and simulation-ready garments, truly capturing the iconic ``Barbie doll'' aesthetic. The core of our framework lies in an expressive 3D representation combined with appropriate modeling constraints. Unlike prior methods, we use G-Shell to uniformly model watertight components (e.g., bodies, shoes) and non-watertight garments. By reformulating boundaries as Euclidean field intersections instead of manifold geodesics, we propose an SDF-based initialization and a hole regularization loss that together achieve a 100x speedup and stable open topology without image input. These disentangled 3D representations are then optimized by specialized expert diffusion models tailored to each domain, ensuring high-fidelity outputs. To mitigate geometric artifacts and texture conflicts when combining different expert models, we further propose several effective geometric losses and strategies. Extensive experiments demonstrate that DreamBarbie outperforms existing methods in both dressed human and outfit generation. Our framework further enables diverse applications, including apparel combination, editing, expressive animation, and physical simulation. Project page: https://xiaokunsun.github.io/DreamBarbie.github.io/.

Chen Zhao, Zhizhou Chen, Yunzhe Xu et al.

Ultra-high-definition (UHD) image restoration faces significant challenges due to its high resolution, complex content, and intricate details. To cope with these challenges, we analyze the restoration process in depth through a progressive spectral perspective, and deconstruct the complex UHD restoration problem into three progressive stages: zero-frequency enhancement, low-frequency restoration, and high-frequency refinement. Building on this insight, we propose a novel framework, ERR, which comprises three collaborative sub-networks: the zero-frequency enhancer (ZFE), the low-frequency restorer (LFR), and the high-frequency refiner (HFR). Specifically, the ZFE integrates global priors to learn global mapping, while the LFR restores low-frequency information, emphasizing reconstruction of coarse-grained content. Finally, the HFR employs our designed frequency-windowed kolmogorov-arnold networks (FW-KAN) to refine textures and details, producing high-quality image restoration. Our approach significantly outperforms previous UHD methods across various tasks, with extensive ablation studies validating the effectiveness of each component. The code is available at \href{https://github.com/NJU-PCALab/ERR}{here}.

Song Wu, Xinyu Chen, Qian Wang et al.

Video editing poses a significant challenge. While a series of tuning-free methods circumvent the need for extensive data collection and model training, they often underutilize the rich information embedded within noisy latent, leading to unsatisfactory results. To address this, we propose a \textit{tuning-free, instruction-based} video editing framework. We approach video editing from the perspective of noisy latent: we design a Structural Noise Initialization Strategy (SNIS) to secure a superior editing starting point by assigning higher noise levels to edited regions (to facilitate content change) and lower noise levels to unedited regions (to maintain content consistency). We introduce a Noise Guidance Mechanism (NGM), which leverages the video prior in the generative model and effectively integrates rich information within the noisy latent to guide the denoising process, thereby preserving unedited content and overall visual coherence. Experiments show that our proposed method achieves better visual quality and state-of-the-art performance.

Dongqi Fan, Tao Chen, Mingjie Wang et al.

Current Pose-Guided Person Image Synthesis (PGPIS) methods depend heavily on large amounts of labeled triplet data to train the generator in a supervised manner. However, they often falter when applied to in-the-wild samples, primarily due to the distribution gap between the training datasets and real-world test samples. While some researchers aim to enhance model generalizability through sophisticated training procedures, advanced architectures, or by creating more diverse datasets, we adopt the test-time fine-tuning paradigm to customize a pre-trained Text2Image (T2I) model. However, naively applying test-time tuning results in inconsistencies in facial identities and appearance attributes. To address this, we introduce a Visual Consistency Module (VCM), which enhances appearance consistency by combining the face, text, and image embedding. Our approach, named OnePoseTrans, requires only a single source image to generate high-quality pose transfer results, offering greater stability than state-of-the-art data-driven methods. For each test case, OnePoseTrans customizes a model in around 48 seconds with an NVIDIA V100 GPU.

Shengrong Gu, Ye Wang, Song Wu et al.

Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively injecting local appearance into a DiT can disrupt its holistic scene structure. We address this by proposing the first training-free framework specifically designed to tame DiTs for high-fidelity appearance transfer. Our core is a synergistic system that disentangles structure and appearance. We leverage high-fidelity inversion to establish a rich content prior for the source image, capturing its lighting and micro-textures. A novel attention-sharing mechanism then dynamically fuses purified appearance features from a reference, guided by geometric priors. Our unified approach operates at 1024px and outperforms specialized methods on tasks ranging from semantic attribute transfer to fine-grained material application. Extensive experiments confirm our state-of-the-art performance in both structural preservation and appearance fidelity.

Zhiqiu Zhang, Dongqi Fan, Mingjie Wang et al.

The goal of image harmonization is to adjust the foreground in a composite image to achieve visual consistency with the background. Recently, latent diffusion model (LDM) are applied for harmonization, achieving remarkable results. However, LDM-based harmonization faces challenges in detail preservation and limited harmonization ability. Additionally, current synthetic datasets rely on color transfer, which lacks local variations and fails to capture complex real-world lighting conditions. To enhance harmonization capabilities, we propose the Region-to-Region transformation. By injecting information from appropriate regions into the foreground, this approach preserves original details while achieving image harmonization or, conversely, generating new composite data. From this perspective, We propose a novel model R2R. Specifically, we design Clear-VAE to preserve high-frequency details in the foreground using Adaptive Filter while eliminating disharmonious elements. To further enhance harmonization, we introduce the Harmony Controller with Mask-aware Adaptive Channel Attention (MACA), which dynamically adjusts the foreground based on the channel importance of both foreground and background regions. To address the limitation of existing datasets, we propose Random Poisson Blending, which transfers color and lighting information from a suitable region to the foreground, thereby generating more diverse and challenging synthetic images. Using this method, we construct a new synthetic dataset, RPHarmony. Experiments demonstrate the superiority of our method over other methods in both quantitative metrics and visual harmony. Moreover, our dataset helps the model generate more realistic images in real examples. Our code, dataset, and model weights have all been released for open access.

Miao Hua, Lijie Liu, Ziyang Cheng et al.

Our task is to remove all facial parts (e.g., eyebrows, eyes, mouth and nose), and then impose visual elements onto the ``blank'' face for augmented reality. Conventional object removal methods rely on image inpainting techniques (e.g., EdgeConnect, HiFill) that are trained in a self-supervised manner with randomly manipulated image pairs. Specifically, given a set of natural images, randomly masked images are used as inputs and the raw images are treated as ground truths. Whereas, this technique does not satisfy the requirements of facial parts removal, as it is hard to obtain ``ground-truth'' images with real ``blank'' faces. To address this issue, we propose a novel data generation technique to produce paired training data that well mimic the ``blank'' faces. In the mean time, we propose a novel network architecture for improved inpainting quality for our task. Finally, we demonstrate various face-oriented augmented reality applications on top of our facial parts removal model. The source codes are released at \href{https://github.com/duxingren14/FaceEraser}{duxingren14/FaceEraser} on github for research purposes.

Zili Yi, Zhiqin Chen, Hao Cai et al.

We introduce BSD-GAN, a novel multi-branch and scale-disentangled training method which enables unconditional Generative Adversarial Networks (GANs) to learn image representations at multiple scales, benefiting a wide range of generation and editing tasks. The key feature of BSD-GAN is that it is trained in multiple branches, progressively covering both the breadth and depth of the network, as resolutions of the training images increase to reveal finer-scale features. Specifically, each noise vector, as input to the generator network of BSD-GAN, is deliberately split into several sub-vectors, each corresponding to, and is trained to learn, image representations at a particular scale. During training, we progressively "de-freeze" the sub-vectors, one at a time, as a new set of higher-resolution images is employed for training and more network layers are added. A consequence of such an explicit sub-vector designation is that we can directly manipulate and even combine latent (sub-vector) codes which model different feature scales.Extensive experiments demonstrate the effectiveness of our training method in scale-disentangled learning of image representations and synthesis of novel image contents, without any extra labels and without compromising quality of the synthesized high-resolution images. We further demonstrate several image generation and manipulation applications enabled or improved by BSD-GAN. Source codes are available at https://github.com/duxingren14/BSD-GAN.

Jiang Lin, Xinyu Chen, Song Wu et al.

Controlling the spatial and semantic structure of diffusion-generated images remains a challenge. Existing methods like ControlNet rely on handcrafted condition maps and retraining, limiting flexibility and generalization. Inversion-based approaches offer stronger alignment but incur high inference cost due to dual-path denoising. We present FreeControl, a training-free framework for semantic structural control in diffusion models. Unlike prior methods that extract attention across multiple timesteps, FreeControl performs one-step attention extraction from a single, optimally chosen key timestep and reuses it throughout denoising. This enables efficient structural guidance without inversion or retraining. To further improve quality and stability, we introduce Latent-Condition Decoupling (LCD): a principled separation of the key timestep and the noised latent used in attention extraction. LCD provides finer control over attention quality and eliminates structural artifacts. FreeControl also supports compositional control via reference images assembled from multiple sources - enabling intuitive scene layout design and stronger prompt alignment. FreeControl introduces a new paradigm for test-time control, enabling structurally and semantically aligned, visually coherent generation directly from raw images, with the flexibility for intuitive compositional design and compatibility with modern diffusion models at approximately 5 percent additional cost.

Song Zhang, Yanlong Chen, Yilin Li et al.

Remote sensing vision-language models (RS-VLMs) face a fundamental mismatch with natural-image counterparts: the same geographic object exhibits radically different visual evidence across ground sampling distances (GSDs) spanning multiple orders of magnitude. Yet existing RS-VLMs often discard GSD or inject it as a discrete text token, forcing a single static parameter set to absorb the entire scale spectrum. We introduce ScaleEarth, a parameter-efficient fine-tuning framework built on Qwen3-VL that treats GSD as a continuous conditioning variable governing the model's computation path. At its core, CS-HLoRA (Continuous Scale-Conditioned Hyper-LoRA) modulates the LoRA low-rank subspace through a GSD-driven gate, enabling the model to dynamically route computation by physical scale. To remove reliance on sensor metadata at deployment, we pair CS-HLoRA with SSE-U, a lightweight heteroscedastic sub-head that predicts GSD and its uncertainty from visual features. To provide matching supervision, we construct GeoScale-VQA, a 1.5M-sample scale-layered RS-VQA corpus whose question-answer generation is conditioned on the same physical scalar that drives CS-HLoRA, forming a closed method-data loop. Trained with QLoRA on an 8B backbone, ScaleEarth achieves state-of-the-art results on remote-sensing benchmarks covering diverse Earth-system tasks, including XLRS-Bench and OmniEarth-Bench.

Dingbao Shao, Song Wu, Shenyi Wang et al.

Due to the scarcity of large-scale in-the-wild triplet data and the improper use of masks, the performance of video virtual try-on models remains limited. In this paper, we first introduce **TripVVT-10K**, the largest and most diverse in-the-wild triplet dataset to date, providing explicit video-level cross-garment supervision that existing video datasets lack. Built upon this resource, we develop **TripVVT**, a Diffusion Transformer-based framework that replaces fragile garment masks with a simple, stable human-mask prior, enabling reliable background preservation while remaining robust to real-world motion, occlusion, and cluttered scenes. To support comprehensive evaluation, we further establish **TripVVT-Bench**, a 100-case benchmark covering diverse garments, complex environments, and multi-person scenarios, with metrics spanning video quality, try-on fidelity, background consistency, and temporal coherence. Compared to state-of-the-art academic and commercial systems, TripVVT achieves superior video quality and garment fidelity while markedly improving generalization to challenging in-the-wild videos. We publicly release the dataset and benchmark, which we believe provide a solid foundation for advancing controllable, realistic, and temporally stable video virtual try-on.

Tianyidan Xie, Peiyu Wang, Yuyi Qian et al.

Physics-aware symbolic simulation of 3D scenes is critical for robotics, embodied AI, and scientific computing, requiring models to understand natural language descriptions of physical phenomena and translate them into executable simulation environments. While large language models (LLMs) excel at general code generation, they struggle with the semantic gap between physical descriptions and simulation implementation. We introduce PhysCodeBench, the first comprehensive benchmark for evaluating physics-aware symbolic simulation, comprising 700 manually-crafted diverse samples across mechanics, fluid dynamics, and soft-body physics with expert annotations. Our evaluation framework measures both code executability and physical accuracy through automated and visual assessment. Building on this, we propose a Self-Corrective Multi-Agent Refinement Framework (SMRF) with three specialized agents (simulation generator, error corrector, and simulation refiner) that collaborate iteratively with domain-specific validation to produce physically accurate simulations. SMRF achieves 67.7 points overall performance compared to 36.3 points for the best baseline among evaluated SOTA models, representing a 31.4-point improvement. Our analysis demonstrates that error correction is critical for accurate physics-aware symbolic simulation and that specialized multi-agent approaches significantly outperform single-agent methods across the tested physical domains.

Tianyidan Xie, Zhentao Huang, Mingjie Wang et al.

Existing image-to-video generation methods often produce physically implausible motions and lack precise control over object dynamics. While prior approaches have incorporated physics simulators, they remain confined to 2D planar motions and fail to capture depth-aware spatial interactions. We introduce PhysLayer, a novel framework enabling language-guided, depth-aware layered animation of static images. PhysLayer consists of three key components: First, a language-guided scene understanding module that utilizes vision foundation models to decompose scenes into depth-based layers by analyzing object composition, material properties, and physical parameters. Second, a depth-aware layered physics simulation that extends 2D rigid-body dynamics with depth motion and perspective-consistent scaling, enabling more realistic object interactions without requiring full 3D reconstruction. Third, a physics-guided video synthesis module that integrates simulated trajectories with scene-aware relighting for temporally coherent results. Experimental results demonstrate improvements in CLIP-Similarity (+2.2\%), FID score (+9.3\%), and Motion-FID (+3\%), with human evaluation showing enhanced physical plausibility (+24\%) and text-video alignment (+35\%). Our approach provides a practical balance between physical realism and computational efficiency for controllable image animation.

Tianyidan Xie, Zhentao Huang, Mingjie Wang et al.

Automated movie creation requires coordinating multiple characters, modalities, and narrative elements across extended sequences -- a challenge that existing end-to-end approaches struggle to address effectively. We present \textbf{CineAGI}, a hierarchical movie generation framework that decomposes this complex task through specialized multi-agent orchestration. Our framework employs three key innovations: (1) a multi-agent narrative synthesis module where specialized LLM agents collaboratively generate comprehensive cinematic blueprints with character profiles, scene descriptions, and cross-modal specifications; (2) a decoupled character-centric pipeline that maintains identity consistency through instance-level tracking and integration while enabling flexible multi-character composition; and (3) a hierarchical audio-visual synchronization mechanism ensuring frame-level alignment of dialogue, expressions, and music. Extensive experiments demonstrate that CineAGI achieves 40\% improvement in overall consistency, 4.4\% gain in subject consistency, 5.4\% enhancement in aesthetic quality, and 28.7\% higher character consistency compared to baselines. Our work establishes a principled foundation for automated multi-scene video generation that preserves narrative coherence and character authenticity.

Tianyidan Xie, Rui Ma, Qian Wang et al.

Recent advancements in image-conditioned image generation have demonstrated substantial progress. However, foreground-conditioned image generation remains underexplored, encountering challenges such as compromised object integrity, foreground-background inconsistencies, limited diversity, and reduced control flexibility. These challenges arise from current end-to-end inpainting models, which suffer from inaccurate training masks, limited foreground semantic understanding, data distribution biases, and inherent interference between visual and textual prompts. To overcome these limitations, we present Anywhere, a multi-agent framework that departs from the traditional end-to-end approach. In this framework, each agent is specialized in a distinct aspect, such as foreground understanding, diversity enhancement, object integrity protection, and textual prompt consistency. Our framework is further enhanced with the ability to incorporate optional user textual inputs, perform automated quality assessments, and initiate re-generation as needed. Comprehensive experiments demonstrate that this modular design effectively overcomes the limitations of existing end-to-end models, resulting in higher fidelity, quality, diversity and controllability in foreground-conditioned image generation. Additionally, the Anywhere framework is extensible, allowing it to benefit from future advancements in each individual agent.

Ye Wang, Ruiqi Liu, Jiang Lin et al.

In this paper, we introduce OmniStyle-1M, a large-scale paired style transfer dataset comprising over one million content-style-stylized image triplets across 1,000 diverse style categories, each enhanced with textual descriptions and instruction prompts. We show that OmniStyle-1M can not only enable efficient and scalable of style transfer models through supervised training but also facilitate precise control over target stylization. Especially, to ensure the quality of the dataset, we introduce OmniFilter, a comprehensive style transfer quality assessment framework, which filters high-quality triplets based on content preservation, style consistency, and aesthetic appeal. Building upon this foundation, we propose OmniStyle, a framework based on the Diffusion Transformer (DiT) architecture designed for high-quality and efficient style transfer. This framework supports both instruction-guided and image-guided style transfer, generating high resolution outputs with exceptional detail. Extensive qualitative and quantitative evaluations demonstrate OmniStyle's superior performance compared to existing approaches, highlighting its efficiency and versatility. OmniStyle-1M and its accompanying methodologies provide a significant contribution to advancing high-quality style transfer, offering a valuable resource for the research community.

Peng Zheng, Tao Liu, Zili Yi et al.

With the development of neural radiance fields and generative models, numerous methods have been proposed for learning 3D human generation from 2D images. These methods allow control over the pose of the generated 3D human and enable rendering from different viewpoints. However, none of these methods explore semantic disentanglement in human image synthesis, i.e., they can not disentangle the generation of different semantic parts, such as the body, tops, and bottoms. Furthermore, existing methods are limited to synthesize images at $512^2$ resolution due to the high computational cost of neural radiance fields. To address these limitations, we introduce SemanticHuman-HD, the first method to achieve semantic disentangled human image synthesis. Notably, SemanticHuman-HD is also the first method to achieve 3D-aware image synthesis at $1024^2$ resolution, benefiting from our proposed 3D-aware super-resolution module. By leveraging the depth maps and semantic masks as guidance for the 3D-aware super-resolution, we significantly reduce the number of sampling points during volume rendering, thereby reducing the computational cost. Our comparative experiments demonstrate the superiority of our method. The effectiveness of each proposed component is also verified through ablation studies. Moreover, our method opens up exciting possibilities for various applications, including 3D garment generation, semantic-aware image synthesis, controllable image synthesis, and out-of-domain image synthesis.

Jiang Lin, Zili Yi

Video style transfer aims to alter the style of a video while preserving its content. Previous methods often struggle with content leakage and style misalignment, particularly when using image-driven approaches that aim to transfer precise styles. In this work, we introduce Trajectory Reset Attention Control (TRAC), a novel method that allows for high-quality style transfer while preserving content integrity. TRAC operates by resetting the denoising trajectory and enforcing attention control, thus enhancing content consistency while significantly reducing the computational costs against inversion-based methods. Additionally, a concept termed Style Medium is introduced to bridge the gap between content and style, enabling a more precise and harmonious transfer of stylistic elements. Building upon these concepts, we present a tuning-free framework that offers a stable, flexible, and efficient solution for both image and video style transfer. Experimental results demonstrate that our proposed framework accommodates a wide range of stylized outputs, from precise content preservation to the production of visually striking results with vibrant and expressive styles.

Ye Wang, Zili Yi, Yibo Zhang et al.

OmniStyle2 introduces a novel approach to artistic style transfer by reframing it as a data problem. Our key insight is destylization, reversing style transfer by removing stylistic elements from artworks to recover natural, style-free counterparts. This yields DST-100K, a large-scale dataset that provides authentic supervision signals by aligning real artistic styles with their underlying content. To build DST-100K, we develop (1) DST, a text-guided destylization model that reconstructs stylefree content, and (2) DST-Filter, a multi-stage evaluation model that employs Chain-of-Thought reasoning to automatically discard low-quality pairs while ensuring content fidelity and style accuracy. Leveraging DST-100K, we train OmniStyle2, a simple feed-forward model based on FLUX.1-dev. Despite its simplicity, OmniStyle2 consistently surpasses state-of-the-art methods across both qualitative and quantitative benchmarks. Our results demonstrate that scalable data generation via destylization provides a reliable supervision paradigm, overcoming the fundamental challenge posed by the lack of ground-truth data in artistic style transfer.

Ye Wang, Zili Yi, Rui Ma

Personalized text-to-image (T2I) models not only produce lifelike and varied visuals but also allow users to tailor the images to fit their personal taste. These personalization techniques can grasp the essence of a concept through a collection of images, or adjust a pre-trained text-to-image model with a specific image input for subject-driven or attribute-aware guidance. Yet, accurately capturing the distinct visual attributes of an individual image poses a challenge for these methods. To address this issue, we introduce OSTAF, a novel parameter-efficient one-shot fine-tuning method which only utilizes one reference image for T2I personalization. A novel hypernetwork-powered attribute-focused fine-tuning mechanism is employed to achieve the precise learning of various attribute features (e.g., appearance, shape or drawing style) from the reference image. Comparing to existing image customization methods, our method shows significant superiority in attribute identification and application, as well as achieves a good balance between efficiency and output quality.

Vishnu Sanjay Ramiya Srinivasan, Rui Ma, Qiang Tang et al.

Recent learning-based inpainting algorithms have achieved compelling results for completing missing regions after removing undesired objects in videos. To maintain the temporal consistency among the frames, 3D spatial and temporal operations are often heavily used in the deep networks. However, these methods usually suffer from memory constraints and can only handle low resolution videos. We propose STRA-Net, a novel spatial-temporal residual aggregation framework for high resolution video inpainting. The key idea is to first learn and apply a spatial and temporal inpainting network on the downsampled low resolution videos. Then, we refine the low resolution results by aggregating the learned spatial and temporal image residuals (details) to the upsampled inpainted frames. Both the quantitative and qualitative evaluations show that we can produce more temporal-coherent and visually appealing results than the state-of-the-art methods on inpainting high resolution videos.

Bingchuan Li, Shaofei Cai, Wei Liu et al.

The semantic controllability of StyleGAN is enhanced by unremitting research. Although the existing weak supervision methods work well in manipulating the style codes along one attribute, the accuracy of manipulating multiple attributes is neglected. Multi-attribute representations are prone to entanglement in the StyleGAN latent space, while sequential editing leads to error accumulation. To address these limitations, we design a Dynamic Style Manipulation Network (DyStyle) whose structure and parameters vary by input samples, to perform nonlinear and adaptive manipulation of latent codes for flexible and precise attribute control. In order to efficient and stable optimization of the DyStyle network, we propose a Dynamic Multi-Attribute Contrastive Learning (DmaCL) method: including dynamic multi-attribute contrastor and dynamic multi-attribute contrastive loss, which simultaneously disentangle a variety of attributes from the generative image and latent space of model. As a result, our approach demonstrates fine-grained disentangled edits along multiple numeric and binary attributes. Qualitative and quantitative comparisons with existing style manipulation methods verify the superiority of our method in terms of the multi-attribute control accuracy and identity preservation without compromising photorealism.

Zili Yi, Qiang Tang, Vishnu Sanjay Ramiya Srinivasan et al.

Advances in deep neural networks have considerably improved the art of animating a still image without operating in 3D domain. Whereas, prior arts can only animate small images (typically no larger than 512x512) due to memory limitations, difficulty of training and lack of high-resolution (HD) training datasets, which significantly reduce their potential for applications in movie production and interactive systems. Motivated by the idea that HD images can be generated by adding high-frequency residuals to low-resolution results produced by a neural network, we propose a novel framework known as Animating Through Warping (ATW) to enable efficient animation of HD images. Specifically, the proposed framework consists of two modules, a novel two-stage neural-network generator and a novel post-processing module known as Animating Through Warping (ATW). It only requires the generator to be trained on small images and can do inference on an image of any size. During inference, an HD input image is decomposed into a low-resolution component(128x128) and its corresponding high-frequency residuals. The generator predicts the low-resolution result as well as the motion field that warps the input face to the desired status (e.g., expressions categories or action units). Finally, the ResWarp module warps the residuals based on the motion field and adding the warped residuals to generates the final HD results from the naively up-sampled low-resolution results. Experiments show the effectiveness and efficiency of our method in generating high-resolution animations. Our proposed framework successfully animates a 4K facial image, which has never been achieved by prior neural models. In addition, our method generally guarantee the temporal coherency of the generated animations. Source codes will be made publicly available.

Zili Yi, Qiang Tang, Shekoofeh Azizi et al.

Recently data-driven image inpainting methods have made inspiring progress, impacting fundamental image editing tasks such as object removal and damaged image repairing. These methods are more effective than classic approaches, however, due to memory limitations they can only handle low-resolution inputs, typically smaller than 1K. Meanwhile, the resolution of photos captured with mobile devices increases up to 8K. Naive up-sampling of the low-resolution inpainted result can merely yield a large yet blurry result. Whereas, adding a high-frequency residual image onto the large blurry image can generate a sharp result, rich in details and textures. Motivated by this, we propose a Contextual Residual Aggregation (CRA) mechanism that can produce high-frequency residuals for missing contents by weighted aggregating residuals from contextual patches, thus only requiring a low-resolution prediction from the network. Since convolutional layers of the neural network only need to operate on low-resolution inputs and outputs, the cost of memory and computing power is thus well suppressed. Moreover, the need for high-resolution training datasets is alleviated. In our experiments, we train the proposed model on small images with resolutions 512x512 and perform inference on high-resolution images, achieving compelling inpainting quality. Our model can inpaint images as large as 8K with considerable hole sizes, which is intractable with previous learning-based approaches. We further elaborate on the light-weight design of the network architecture, achieving real-time performance on 2K images on a GTX 1080 Ti GPU. Codes are available at: Atlas200dk/sample-imageinpainting-HiFill.

Zili Yi, Hao Zhang, Ping Tan et al.

Conditional Generative Adversarial Networks (GANs) for cross-domain image-to-image translation have made much progress recently. Depending on the task complexity, thousands to millions of labeled image pairs are needed to train a conditional GAN. However, human labeling is expensive, even impractical, and large quantities of data may not always be available. Inspired by dual learning from natural language translation, we develop a novel dual-GAN mechanism, which enables image translators to be trained from two sets of unlabeled images from two domains. In our architecture, the primal GAN learns to translate images from domain U to those in domain V, while the dual GAN learns to invert the task. The closed loop made by the primal and dual tasks allows images from either domain to be translated and then reconstructed. Hence a loss function that accounts for the reconstruction error of images can be used to train the translators. Experiments on multiple image translation tasks with unlabeled data show considerable performance gain of DualGAN over a single GAN. For some tasks, DualGAN can even achieve comparable or slightly better results than conditional GAN trained on fully labeled data.