Inpainting
-
Image Restoration via Primal Dual Hybrid Gradient and Flow Generative Model
2025-11-10 06:26:36Ji Li, Chao WangAbstract
Regularized optimization has been a classical approach to solving imaging inverse problems, where the regularization term enforces desirable properties of the unknown image. Recently, the integration of flow matching generative models into image restoration has garnered significant attention, owing to their powerful prior modeling capabilities. In this work, we incorporate such generative priors into a Plug-and-Play (PnP) framework based on proximal splitting, where the proximal operator associated with the regularizer is replaced by a time-dependent denoiser derived from the generative model. While existing PnP methods have achieved notable success in inverse problems with smooth squared $\ell_2$ data fidelity--typically associated with Gaussian noise--their applicability to more general data fidelity terms remains underexplored. To address this, we propose a general and efficient PnP algorithm inspired by the primal-dual hybrid gradient (PDHG) method. Our approach is computationally efficient, memory-friendly, and accommodates a wide range of fidelity terms. In particular, it supports both $\ell_1$ and $\ell_2$ norm-based losses, enabling robustness to non-Gaussian noise types such as Poisson and impulse noise. We validate our method on several image restoration tasks, including denoising, super-resolution, deblurring, and inpainting, and demonstrate that $\ell_1$ and $\ell_2$ fidelity terms outperform the conventional squared $\ell_2$ loss in the presence of non-Gaussian noise.
Abstract (translated)
URL
https://arxiv.org/abs/2511.06748
PDF
-
AvatarTex: High-Fidelity Facial Texture Reconstruction from Single-Image Stylized Avatars
2025-11-10 05:31:15Yuda Qiu, Zitong Xiao, Yiwei Zuo, Zisheng Ye, Weikai Chen, Xiaoguang HanAbstract
We present AvatarTex, a high-fidelity facial texture reconstruction framework capable of generating both stylized and photorealistic textures from a single image. Existing methods struggle with stylized avatars due to the lack of diverse multi-style datasets and challenges in maintaining geometric consistency in non-standard textures. To address these limitations, AvatarTex introduces a novel three-stage diffusion-to-GAN pipeline. Our key insight is that while diffusion models excel at generating diversified textures, they lack explicit UV constraints, whereas GANs provide a well-structured latent space that ensures style and topology consistency. By integrating these strengths, AvatarTex achieves high-quality topology-aligned texture synthesis with both artistic and geometric coherence. Specifically, our three-stage pipeline first completes missing texture regions via diffusion-based inpainting, refines style and structure consistency using GAN-based latent optimization, and enhances fine details through diffusion-based repainting. To address the need for a stylized texture dataset, we introduce TexHub, a high-resolution collection of 20,000 multi-style UV textures with precise UV-aligned layouts. By leveraging TexHub and our structured diffusion-to-GAN pipeline, AvatarTex establishes a new state-of-the-art in multi-style facial texture reconstruction. TexHub will be released upon publication to facilitate future research in this field.
Abstract (translated)
URL
https://arxiv.org/abs/2511.06721
PDF
-
UniADC: A Unified Framework for Anomaly Detection and Classification
2025-11-10 02:42:08Ximiao Zhang, Min Xu, Zheng Zhang, Junlin Hu, Xiuzhuang ZhouAbstract
In this paper, we introduce the task of unified anomaly detection and classification, which aims to simultaneously detect anomalous regions in images and identify their specific categories. Existing methods typically treat anomaly detection and classification as separate tasks, thereby neglecting their inherent correlation, limiting information sharing, and resulting in suboptimal performance. To address this, we propose UniADC, a unified anomaly detection and classification model that can effectively perform both tasks with only a few or even no anomaly images. Specifically, UniADC consists of two key components: a training-free controllable inpainting network and a multi-task discriminator. The inpainting network can synthesize anomaly images of specific categories by repainting normal regions guided by anomaly priors, and can also repaint few-shot anomaly samples to augment the available anomaly data. The multi-task discriminator is then trained on these synthesized samples, enabling precise anomaly detection and classification by aligning fine-grained image features with anomaly-category embeddings. We conduct extensive experiments on three anomaly detection and classification datasets, including MVTec-FS, MTD, and WFDD, and the results demonstrate that UniADC consistently outperforms existing methods in anomaly detection, localization, and classification. The code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2511.06644
PDF
-
Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360{deg} Scenes
2025-11-09 16:47:30Shaoxiang Wang, Shihong Zhang, Christen Millerdurai, R\"udiger Westermann, Didier Stricker, Alain PaganiAbstract
Despite recent advances in single-object front-facing inpainting using NeRF and 3D Gaussian Splatting (3DGS), inpainting in complex 360° scenes remains largely underexplored. This is primarily due to three key challenges: (i) identifying target objects in the 3D field of 360° environments, (ii) dealing with severe occlusions in multi-object scenes, which makes it hard to define regions to inpaint, and (iii) maintaining consistent and high-quality appearance across views effectively. To tackle these challenges, we propose Inpaint360GS, a flexible 360° editing framework based on 3DGS that supports multi-object removal and high-fidelity inpainting in 3D space. By distilling 2D segmentation into 3D and leveraging virtual camera views for contextual guidance, our method enables accurate object-level editing and consistent scene completion. We further introduce a new dataset tailored for 360° inpainting, addressing the lack of ground truth object-free scenes. Experiments demonstrate that Inpaint360GS outperforms existing baselines and achieves state-of-the-art performance. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2511.06457
PDF
-
Assessing Identity Leakage in Talking Face Generation: Metrics and Evaluation Framework
2025-11-05 17:11:53Dogucan Yaman, Fevziye Irem Eyiokur, Haz{\i}m Kemal Ekenel, Alexander WaibelAbstract
Inpainting-based talking face generation aims to preserve video details such as pose, lighting, and gestures while modifying only lip motion, often using an identity reference image to maintain speaker consistency. However, this mechanism can introduce lip leaking, where generated lips are influenced by the reference image rather than solely by the driving audio. Such leakage is difficult to detect with standard metrics and conventional test setup. To address this, we propose a systematic evaluation methodology to analyze and quantify lip leakage. Our framework employs three complementary test setups: silent-input generation, mismatched audio-video pairing, and matched audio-video synthesis. We also introduce derived metrics including lip-sync discrepancy and silent-audio-based lip-sync scores. In addition, we study how different identity reference selections affect leakage, providing insights into reference design. The proposed methodology is model-agnostic and establishes a more reliable benchmark for future research in talking face generation.
Abstract (translated)
URL
https://arxiv.org/abs/2511.08613
PDF
-
SyMuPe: Affective and Controllable Symbolic Music Performance
2025-11-05 12:42:08Ilya Borovik, Dmitrii Gavrilev, Vladimir ViroAbstract
Emotions are fundamental to the creation and perception of music performances. However, achieving human-like expression and emotion through machine learning models for performance rendering remains a challenging task. In this work, we present SyMuPe, a novel framework for developing and training affective and controllable symbolic piano performance models. Our flagship model, PianoFlow, uses conditional flow matching trained to solve diverse multi-mask performance inpainting tasks. By design, it supports both unconditional generation and infilling of music performance features. For training, we use a curated, cleaned dataset of 2,968 hours of aligned musical scores and expressive MIDI performances. For text and emotion control, we integrate a piano performance emotion classifier and tune PianoFlow with the emotion-weighted Flan-T5 text embeddings provided as conditional inputs. Objective and subjective evaluations against transformer-based baselines and existing models show that PianoFlow not only outperforms other approaches, but also achieves performance quality comparable to that of human-recorded and transcribed MIDI samples. For emotion control, we present and analyze samples generated under different text conditioning scenarios. The developed model can be integrated into interactive applications, contributing to the creation of more accessible and engaging music performance systems.
Abstract (translated)
URL
https://arxiv.org/abs/2511.03425
PDF
-
Unified Long Video Inpainting and Outpainting via Overlapping High-Order Co-Denoising
2025-11-05 08:09:03Shuangquan Lyu, Steven Mao, Yue MaAbstract
Generating long videos remains a fundamental challenge, and achieving high controllability in video inpainting and outpainting is particularly demanding. To address both of these challenges simultaneously and achieve controllable video inpainting and outpainting for long video clips, we introduce a novel and unified approach for long video inpainting and outpainting that extends text-to-video diffusion models to generate arbitrarily long, spatially edited videos with high fidelity. Our method leverages LoRA to efficiently fine-tune a large pre-trained video diffusion model like Alibaba's Wan 2.1 for masked region video synthesis, and employs an overlap-and-blend temporal co-denoising strategy with high-order solvers to maintain consistency across long sequences. In contrast to prior work that struggles with fixed-length clips or exhibits stitching artifacts, our system enables arbitrarily long video generation and editing without noticeable seams or drift. We validate our approach on challenging inpainting/outpainting tasks including editing or adding objects over hundreds of frames and demonstrate superior performance to baseline methods like Wan 2.1 model and VACE in terms of quality (PSNR/SSIM), and perceptual realism (LPIPS). Our method enables practical long-range video editing with minimal overhead, achieved a balance between parameter efficient and superior performance.
Abstract (translated)
URL
https://arxiv.org/abs/2511.03272
PDF
-
KAO: Kernel-Adaptive Optimization in Diffusion for Satellite Image
2025-11-04 10:44:36Teerapong PanboonyuenAbstract
Satellite image inpainting is a crucial task in remote sensing, where accurately restoring missing or occluded regions is essential for robust image analysis. In this paper, we propose KAO, a novel framework that utilizes Kernel-Adaptive Optimization within diffusion models for satellite image inpainting. KAO is specifically designed to address the challenges posed by very high-resolution (VHR) satellite datasets, such as DeepGlobe and the Massachusetts Roads Dataset. Unlike existing methods that rely on preconditioned models requiring extensive retraining or postconditioned models with significant computational overhead, KAO introduces a Latent Space Conditioning approach, optimizing a compact latent space to achieve efficient and accurate inpainting. Furthermore, we incorporate Explicit Propagation into the diffusion process, facilitating forward-backward fusion, which improves the stability and precision of the method. Experimental results demonstrate that KAO sets a new benchmark for VHR satellite image restoration, providing a scalable, high-performance solution that balances the efficiency of preconditioned models with the flexibility of postconditioned models.
Abstract (translated)
URL
https://arxiv.org/abs/2511.02462
PDF
-
Locally-Supervised Global Image Restoration
2025-11-03 19:12:25Benjamin Walder, Daniel Toader, Robert Nuster, G\"unther Paltauf, Peter Burgholzer, Gregor Langer, Lukas Krainer, Markus HaltmeierAbstract
We address the problem of image reconstruction from incomplete measurements, encompassing both upsampling and inpainting, within a learning-based framework. Conventional supervised approaches require fully sampled ground truth data, while self-supervised methods allow incomplete ground truth but typically rely on random sampling that, in expectation, covers the entire image. In contrast, we consider fixed, deterministic sampling patterns with inherently incomplete coverage, even in expectation. To overcome this limitation, we exploit multiple invariances of the underlying image distribution, which theoretically allows us to achieve the same reconstruction performance as fully supervised approaches. We validate our method on optical-resolution image upsampling in photoacoustic microscopy (PAM), demonstrating competitive or superior results while requiring substantially less ground truth data.
Abstract (translated)
URL
https://arxiv.org/abs/2511.01998
PDF
-
SecDiff: Diffusion-Aided Secure Deep Joint Source-Channel Coding Against Adversarial Attacks
2025-11-03 11:24:06Changyuan Zhao, Jiacheng Wang, Ruichen Zhang, Dusit Niyato, Hongyang Du, Zehui Xiong, Dong In Kim, Ping ZhangAbstract
Deep joint source-channel coding (JSCC) has emerged as a promising paradigm for semantic communication, delivering significant performance gains over conventional separate coding schemes. However, existing JSCC frameworks remain vulnerable to physical-layer adversarial threats, such as pilot spoofing and subcarrier jamming, compromising semantic fidelity. In this paper, we propose SecDiff, a plug-and-play, diffusion-aided decoding framework that significantly enhances the security and robustness of deep JSCC under adversarial wireless environments. Different from prior diffusion-guided JSCC methods that suffer from high inference latency, SecDiff employs pseudoinverse-guided sampling and adaptive guidance weighting, enabling flexible step-size control and efficient semantic reconstruction. To counter jamming attacks, we introduce a power-based subcarrier masking strategy and recast recovery as a masked inpainting problem, solved via diffusion guidance. For pilot spoofing, we formulate channel estimation as a blind inverse problem and develop an expectation-minimization (EM)-driven reconstruction algorithm, guided jointly by reconstruction loss and a channel operator. Notably, our method alternates between pilot recovery and channel estimation, enabling joint refinement of both variables throughout the diffusion process. Extensive experiments over orthogonal frequency-division multiplexing (OFDM) channels under adversarial conditions show that SecDiff outperforms existing secure and generative JSCC baselines by achieving a favorable trade-off between reconstruction quality and computational cost. This balance makes SecDiff a promising step toward practical, low-latency, and attack-resilient semantic communications.
Abstract (translated)
URL
https://arxiv.org/abs/2511.01466
PDF
-
Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning
2025-10-31 16:30:08Yuhong Liu, Beichen Zhang, Yuhang Zang, Yuhang Cao, Long Xing, Xiaoyi Dong, Haodong Duan, Dahua Lin, Jiaqi WangAbstract
Spatial understanding remains a weakness of Large Vision-Language Models (LVLMs). Existing supervised fine-tuning (SFT) and recent reinforcement learning with verifiable rewards (RLVR) pipelines depend on costly supervision, specialized tools, or constrained environments that limit scale. We introduce Spatial-SSRL, a self-supervised RL paradigm that derives verifiable signals directly from ordinary RGB or RGB-D images. Spatial-SSRL automatically formulates five pretext tasks that capture 2D and 3D spatial structure: shuffled patch reordering, flipped patch recognition, cropped patch inpainting, regional depth ordering, and relative 3D position prediction. These tasks provide ground-truth answers that are easy to verify and require no human or LVLM annotation. Training on our tasks substantially improves spatial reasoning while preserving general visual capabilities. On seven spatial understanding benchmarks in both image and video settings, Spatial-SSRL delivers average accuracy gains of 4.63% (3B) and 3.89% (7B) over the Qwen2.5-VL baselines. Our results show that simple, intrinsic supervision enables RLVR at scale and provides a practical route to stronger spatial intelligence in LVLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2510.27606
PDF
-
SEE4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting
2025-10-30 17:59:39Dongyue Lu, Ao Liang, Tianxin Huang, Xiao Fu, Yuyang Zhao, Baorui Ma, Liang Pan, Wei Yin, Lingdong Kong, Wei Tsang Ooi, Ziwei LiuAbstract
Immersive applications call for synthesizing spatiotemporal 4D content from casual videos without costly 3D supervision. Existing video-to-4D methods typically rely on manually annotated camera poses, which are labor-intensive and brittle for in-the-wild footage. Recent warp-then-inpaint approaches mitigate the need for pose labels by warping input frames along a novel camera trajectory and using an inpainting model to fill missing regions, thereby depicting the 4D scene from diverse viewpoints. However, this trajectory-to-trajectory formulation often entangles camera motion with scene dynamics and complicates both modeling and inference. We introduce SEE4D, a pose-free, trajectory-to-camera framework that replaces explicit trajectory prediction with rendering to a bank of fixed virtual cameras, thereby separating camera control from scene modeling. A view-conditional video inpainting model is trained to learn a robust geometry prior by denoising realistically synthesized warped images and to inpaint occluded or missing regions across virtual viewpoints, eliminating the need for explicit 3D annotations. Building on this inpainting core, we design a spatiotemporal autoregressive inference pipeline that traverses virtual-camera splines and extends videos with overlapping windows, enabling coherent generation at bounded per-step complexity. We validate See4D on cross-view video generation and sparse reconstruction benchmarks. Across quantitative metrics and qualitative assessments, our method achieves superior generalization and improved performance relative to pose- or trajectory-conditioned baselines, advancing practical 4D world modeling from casual videos.
Abstract (translated)
URL
https://arxiv.org/abs/2510.26796
PDF
-
Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics
2025-10-30 10:17:27Zhiyang Xun, Shivam Gupta, Eric PriceAbstract
Given a noisy linear measurement $y = Ax + \xi$ of a distribution $p(x)$, and a good approximation to the prior $p(x)$, when can we sample from the posterior $p(x \mid y)$? Posterior sampling provides an accurate and fair framework for tasks such as inpainting, deblurring, and MRI reconstruction, and several heuristics attempt to approximate it. Unfortunately, approximate posterior sampling is computationally intractable in general. To sidestep this hardness, we focus on (local or global) log-concave distributions $p(x)$. In this regime, Langevin dynamics yields posterior samples when the exact scores of $p(x)$ are available, but it is brittle to score--estimation error, requiring an MGF bound (sub-exponential error). By contrast, in the unconditional setting, diffusion models succeed with only an $L^2$ bound on the score error. We prove that combining diffusion models with an annealed variant of Langevin dynamics achieves conditional sampling in polynomial time using merely an $L^4$ bound on the score error.
Abstract (translated)
URL
https://arxiv.org/abs/2510.26324
PDF
-
Security Risk of Misalignment between Text and Image in Multi-modal Model
2025-10-30 03:31:20Xiaosen Wang, Zhijin Ge, Shaokang WangAbstract
Despite the notable advancements and versatility of multi-modal diffusion models, such as text-to-image models, their susceptibility to adversarial inputs remains underexplored. Contrary to expectations, our investigations reveal that the alignment between textual and Image modalities in existing diffusion models is inadequate. This misalignment presents significant risks, especially in the generation of inappropriate or Not-Safe-For-Work (NSFW) content. To this end, we propose a novel attack called Prompt-Restricted Multi-modal Attack (PReMA) to manipulate the generated content by modifying the input image in conjunction with any specified prompt, without altering the prompt itself. PReMA is the first attack that manipulates model outputs by solely creating adversarial images, distinguishing itself from prior methods that primarily generate adversarial prompts to produce NSFW content. Consequently, PReMA poses a novel threat to the integrity of multi-modal diffusion models, particularly in image-editing applications that operate with fixed prompts. Comprehensive evaluations conducted on image inpainting and style transfer tasks across various models confirm the potent efficacy of PReMA.
Abstract (translated)
URL
https://arxiv.org/abs/2510.26105
PDF
-
OmniText: A Training-Free Generalist for Controllable Text-Image Manipulation
2025-10-28 06:06:52Agus Gunawan, Samuel Teodoro, Yun Chen, Soo Ye Kim, Jihyong Oh, Munchurl KimAbstract
Recent advancements in diffusion-based text synthesis have demonstrated significant performance in inserting and editing text within images via inpainting. However, despite the potential of text inpainting methods, three key limitations hinder their applicability to broader Text Image Manipulation (TIM) tasks: (i) the inability to remove text, (ii) the lack of control over the style of rendered text, and (iii) a tendency to generate duplicated letters. To address these challenges, we propose OmniText, a training-free generalist capable of performing a wide range of TIM tasks. Specifically, we investigate two key properties of cross- and self-attention mechanisms to enable text removal and to provide control over both text styles and content. Our findings reveal that text removal can be achieved by applying self-attention inversion, which mitigates the model's tendency to focus on surrounding text, thus reducing text hallucinations. Additionally, we redistribute cross-attention, as increasing the probability of certain text tokens reduces text hallucination. For controllable inpainting, we introduce novel loss functions in a latent optimization framework: a cross-attention content loss to improve text rendering accuracy and a self-attention style loss to facilitate style customization. Furthermore, we present OmniText-Bench, a benchmark dataset for evaluating diverse TIM tasks. It includes input images, target text with masks, and style references, covering diverse applications such as text removal, rescaling, repositioning, and insertion and editing with various styles. Our OmniText framework is the first generalist method capable of performing diverse TIM tasks. It achieves state-of-the-art performance across multiple tasks and metrics compared to other text inpainting methods and is comparable with specialist methods.
Abstract (translated)
URL
https://arxiv.org/abs/2510.24093
PDF
-
Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling
2025-10-27 17:59:51Shuhong Zheng, Ashkan Mirzaei, Igor GilitschenskiAbstract
Current 3D/4D generation methods are usually optimized for photorealism, efficiency, and aesthetics. However, they often fail to preserve the semantic identity of the subject across different viewpoints. Adapting generation methods with one or few images of a specific subject (also known as Personalization or Subject-driven generation) allows generating visual content that align with the identity of the subject. However, personalized 3D/4D generation is still largely underexplored. In this work, we introduce TIRE (Track, Inpaint, REsplat), a novel method for subject-driven 3D/4D generation. It takes an initial 3D asset produced by an existing 3D generative model as input and uses video tracking to identify the regions that need to be modified. Then, we adopt a subject-driven 2D inpainting model for progressively infilling the identified regions. Finally, we resplat the modified 2D multi-view observations back to 3D while still maintaining consistency. Extensive experiments demonstrate that our approach significantly improves identity preservation in 3D/4D generation compared to state-of-the-art methods. Our project website is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2510.23605
PDF
-
UniAIDet: A Unified and Universal Benchmark for AI-Generated Image Content Detection and Localization
Abstract
With the rapid proliferation of image generative models, the authenticity of digital images has become a significant concern. While existing studies have proposed various methods for detecting AI-generated content, current benchmarks are limited in their coverage of diverse generative models and image categories, often overlooking end-to-end image editing and artistic images. To address these limitations, we introduce UniAIDet, a unified and comprehensive benchmark that includes both photographic and artistic images. UniAIDet covers a wide range of generative models, including text-to-image, image-to-image, image inpainting, image editing, and deepfake models. Using UniAIDet, we conduct a comprehensive evaluation of various detection methods and answer three key research questions regarding generalization capability and the relation between detection and localization. Our benchmark and analysis provide a robust foundation for future research.
Abstract (translated)
URL
https://arxiv.org/abs/2510.23023
PDF
-
WorldGrow: Generating Infinite 3D World
2025-10-24 17:39:52Sikuang Li, Chen Yang, Jiemin Fang, Taoran Yi, Jia Lu, Jiazhong Cen, Lingxi Xie, Wei Shen, Qi TianAbstract
We tackle the challenge of generating the infinitely extendable 3D world -- large, continuous environments with coherent geometry and realistic appearance. Existing methods face key challenges: 2D-lifting approaches suffer from geometric and appearance inconsistencies across views, 3D implicit representations are hard to scale up, and current 3D foundation models are mostly object-centric, limiting their applicability to scene-level generation. Our key insight is leveraging strong generation priors from pre-trained 3D models for structured scene block generation. To this end, we propose WorldGrow, a hierarchical framework for unbounded 3D scene synthesis. Our method features three core components: (1) a data curation pipeline that extracts high-quality scene blocks for training, making the 3D structured latent representations suitable for scene generation; (2) a 3D block inpainting mechanism that enables context-aware scene extension; and (3) a coarse-to-fine generation strategy that ensures both global layout plausibility and local geometric/textural fidelity. Evaluated on the large-scale 3D-FRONT dataset, WorldGrow achieves SOTA performance in geometry reconstruction, while uniquely supporting infinite scene generation with photorealistic and structurally consistent outputs. These results highlight its capability for constructing large-scale virtual environments and potential for building future world models.
Abstract (translated)
URL
https://arxiv.org/abs/2510.21682
PDF
-
VidSplice: Towards Coherent Video Inpainting via Explicit Spaced Frame Guidance
2025-10-24 13:44:09Ming Xie, Junqiu Yu, Qiaole Dong, Xiangyang Xue, Yanwei FuAbstract
Recent video inpainting methods often employ image-to-video (I2V) priors to model temporal consistency across masked frames. While effective in moderate cases, these methods struggle under severe content degradation and tend to overlook spatiotemporal stability, resulting in insufficient control over the latter parts of the video. To address these limitations, we decouple video inpainting into two sub-tasks: multi-frame consistent image inpainting and masked area motion propagation. We propose VidSplice, a novel framework that introduces spaced-frame priors to guide the inpainting process with spatiotemporal cues. To enhance spatial coherence, we design a CoSpliced Module to perform first-frame propagation strategy that diffuses the initial frame content into subsequent reference frames through a splicing mechanism. Additionally, we introduce a delicate context controller module that encodes coherent priors after frame duplication and injects the spliced video into the I2V generative backbone, effectively constraining content distortion during generation. Extensive evaluations demonstrate that VidSplice achieves competitive performance across diverse video inpainting scenarios. Moreover, its design significantly improves both foreground alignment and motion stability, outperforming existing approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2510.21461
PDF
-
Neural Variational Dropout Processes
2025-10-22 09:45:44Insu Jeon, Youngjin Park, Gunhee KimAbstract
Learning to infer the conditional posterior model is a key step for robust meta-learning. This paper presents a new Bayesian meta-learning approach called Neural Variational Dropout Processes (NVDPs). NVDPs model the conditional posterior distribution based on a task-specific dropout; a low-rank product of Bernoulli experts meta-model is utilized for a memory-efficient mapping of dropout rates from a few observed contexts. It allows for a quick reconfiguration of a globally learned and shared neural network for new tasks in multi-task few-shot learning. In addition, NVDPs utilize a novel prior conditioned on the whole task data to optimize the conditional \textit{dropout} posterior in the amortized variational inference. Surprisingly, this enables the robust approximation of task-specific dropout rates that can deal with a wide range of functional ambiguities and uncertainties. We compared the proposed method with other meta-learning approaches in the few-shot learning tasks such as 1D stochastic regression, image inpainting, and classification. The results show the excellent performance of NVDPs.
Abstract (translated)
学习推断条件后验模型是鲁棒元学习的关键步骤。本文提出了一种新的贝叶斯元学习方法，称为神经变分Dropout过程（Neural Variational Dropout Processes，NVDP）。NVDP基于任务特定的dropout来建模条件后验分布；采用低秩伯努利专家元模型的乘积，以记忆高效的方式从少数观察到的情境中映射dropout率。这使得能够快速重新配置一个全局学习并共享的神经网络，以便为多任务少样本学习中的新任务进行调整。 此外，NVDP使用了一种新颖的任务数据整体条件下的先验，在近似变分推理中优化条件*dropout*后验。令人惊讶的是，这种方法能够鲁棒地逼近处理各种功能性模糊性和不确定性的情况下特定任务的dropout率。 我们将在1D随机回归、图像修复和分类等少样本学习任务上，将所提出的方法与其他元学习方法进行了比较。结果显示NVDPs具有出色的性能。
URL
https://arxiv.org/abs/2510.19425
PDF
