论文检索

Wenbo Nie, Lang Nie, Chunyu Lin, Jingwen Chen, Ke Xing, Jiyuan Wang, Kang Liao

Wide-angle cameras, despite their popularity for content creation, suffer from distortion-induced facial stretching—especially at the edge of the lens—which degrades visual appeal. To address this issue, we propose a structure-to-detail portrait correction model named ImagePC. It integrates the long-range awareness of the transformer and multi-step denoising of diffusion models into a unified framework, achieving global structural robustness and local detail refinement. Besides, considering the high cost of obtaining video labels, we then repurpose ImagePC for unlabeled wide-angle videos (termed VideoPC), by spatiotemporal diffusion adaption with spatial consistency and temporal smoothness constraints. For the former, we encourage the denoised image to approximate pseudo labels following the wide-angle distortion distribution pattern, while for the latter, we derive rectification trajectories with backward optical flows and smooth them. Compared with ImagePC, VideoPC maintains high-quality facial corrections in space and mitigates the potential temporal shakes sequentially in blind scenarios. Finally, to establish an evaluation benchmark and train the framework, we establish a video portrait dataset with a large diversity in the number of people, lighting conditions, and background. Experiments demonstrate that the proposed methods outperform existing solutions quantitatively and qualitatively, contributing to high-fidelity wide-angle videos with stable and natural portraits.

Kang Ni, Minrui Zou, Yuxuan Li, Xiang Li, Kehua Guo, Ming-Ming Cheng, Yimian Dai

One of the primary challenges in Synthetic Aperture Radar (SAR) object detection lies in the pervasive influence of coherent noise. As a common practice, most existing methods, whether handcrafted approaches or deep learning-based methods, employ the analysis or enhancement of object spatial-domain characteristics to achieve implicit denoising. In this paper, we propose DenoDet V2, which explores a completely novel and different perspective to deconstruct and modulate the features in the transform domain via a carefully designed attention architecture. Compared to DenoDet V1, DenoDet V2 is a major advancement that exploits the complementary nature of amplitude and phase information through a band-wise mutual modulation mechanism, which enables a reciprocal enhancement between phase and amplitude spectra. Extensive experiments on various SAR datasets demonstrate the state-of-the-art performance of DenoDet V2. Notably, DenoDet V2 achieves a significant 0.8% improvement on SARDet-100K dataset compared to DenoDet V1, while reducing the model complexity by half.

Hoang-Nhat Nguyen

Identical twin face verification represents an extreme fine-grained recognition challenge where even state-of-the-art systems fail due to overwhelming genetic similarity. Current face recognition methods achieve over 99.8% accuracy on standard benchmarks but drop dramatically to 88.9% when distinguishing identical twins, exposing critical vulnerabilities in biometric security systems. The difficulty lies in learning features that capture subtle, non-genetic variations that uniquely identify individuals. We propose the Asymmetric Hierarchical Attention Network (AHAN), a novel architecture specifically designed for this challenge through multi-granularity facial analysis. AHAN introduces a Hierarchical Cross-Attention (HCA) module that performs multi-scale analysis on semantic facial regions, enabling specialized processing at optimal resolutions. We further propose a Facial Asymmetry Attention Module (FAAM) that learns unique biometric signatures by computing cross-attention between left and right facial halves, capturing subtle asymmetric patterns that differ even between twins. To ensure the network learns truly individuating features, we introduce Twin-Aware Pair-Wise Cross-Attention (TA-PWCA), a training-only regularization strategy that uses each subject's own twin as the hardest possible distractor. Extensive experiments on the ND TWIN dataset demonstrate that AHAN achieves 92.3% twin verification accuracy, representing a 3.4 percentage point improvement over state-of-the-art methods.

Davide Napolitano, Luca Cagliero, Fabrizio Battiloro

The evolution of Visual Large Language Models (VLLMs) has revolutionized the automatic understanding of Visually Rich Documents (VRDs), which contain both textual and visual elements. Although VLLMs excel in Visual Question Answering (VQA) on multi-page VRDs, their ability to detect unanswerable questions is still an open research question. Our research delves into the robustness of the VLLMs to plausible yet unanswerable questions, i.e., questions that appear valid but cannot be answered due to subtle corruptions caused by swaps between related concepts or plausible question formulations. Corruptions are generated by replacing the original natural language entities with other ones of the same type, belonging to different document elements, and in different layout positions or pages of the related document. To this end, we present VRD-UQA (VISUALLY RICH DOCUMENT UNANSWERABLE QUESTION ANSWERING), a benchmark for evaluating VLLMs' resilience to plausible yet unanswerable questions across multiple dimensions. It automatically alters the questions of existing VQA datasets consisting of multi-page VRDs, verifies their unanswerability using a VLLM-as-a-judge approach, and then thoroughly evaluates VLLMs' performance. Experiments, run on 12 models, analyze: (1) The VLLMs' accuracy in detecting unanswerable questions at both page and document levels; (2) The effect of different types of corruption (NLP entity, document element, layout); (3) The effectiveness of different knowledge injection strategies based on in-context learning (OCR, multi-page selection, or the possibility of unanswerability). Our findings reveal VLLMs' limitations and demonstrate that VRD-UQA can serve as an evaluation framework for developing resilient document VQA systems.

Lingzhou Mu, Wang Qiang, Fan Jiang, Mengchao Wang, Mu Xu, Kai Zhang

Human-Scene Interaction (HSI) seeks to generate realistic human behaviors within complex environments, yet it faces significant challenges in handling long-horizon, high-level tasks and generalizing to unseen scenes. To address these limitations, we introduce FantasyHSI, a novel HSI framework centered on video generation and multi-agent systems that operates without paired data. We model the complex interaction process as a dynamic directed graph, upon which we build a collaborative multi-agent system. This system comprises a scene navigator agent for environmental perception and high-level path planning, and a planning agent that decomposes long-horizon goals into atomic actions. Critically, we introduce a critic agent that establishes a closed-loop feedback mechanism by evaluating the deviation between generated actions and the planned path. This allows for the dynamic correction of trajectory drifts caused by the stochasticity of the generative model, thereby ensuring long-term logical consistency. To enhance the physical realism of the generated motions, we leverage Direct Preference Optimization (DPO) to train the action generator, significantly reducing artifacts such as limb distortion and foot-sliding. Extensive experiments on our custom SceneBench benchmark demonstrate that FantasyHSI significantly outperforms existing methods in terms of generalization, long-horizon task completion, and physical realism.

Andrey Moskalenko, Danil Kuznetsov, Irina Dudko, Anastasiia Iasakova, Nikita Boldyrev, Denis Shepelev, Andrei Spiridonov, Andrey Kuznetsov, Vlad Shakhuro

Promptable segmentation models such as SAM have established a powerful paradigm, enabling strong generalization to unseen objects and domains with minimal user input, including points, bounding boxes, and text prompts. Among these, bounding boxes stand out as particularly effective, often outperforming points while significantly reducing annotation costs. However, current training and evaluation protocols typically rely on synthetic prompts generated through simple heuristics, offering limited insight into real-world robustness. In this paper, we investigate the robustness of promptable segmentation models to natural variations in bounding box prompts. First, we conduct a controlled user study and collect thousands of real bounding box annotations. Our analysis reveals substantial variability in segmentation quality across users for the same model and instance, indicating that SAM-like models are highly sensitive to natural prompt noise. Then, since exhaustive testing of all possible user inputs is computationally prohibitive, we reformulate robustness evaluation as a white-box optimization problem over the bounding box prompt space. We introduce BREPS, a method for generating adversarial bounding boxes that minimize or maximize segmentation error while adhering to naturalness constraints. Finally, we benchmark state-of-the-art models across 10 datasets, spanning everyday scenes to medical imaging.

Xunyue Mo, Weibin Wu, Qingrui Tu, Hang Wang, Junxi He, Zibin Zheng

Latent Diffusion Models (LDMs) have achieved remarkable success in image generation tasks, yet their low barrier to customization poses severe threats related to art plagiarism. As a countermeasure, adversarial methods have been proposed to protect artworks from plagiarism. However, current methods suffer from limited effectiveness, high cost, and complex optimization. Moreover, their exploration and exploitation of LDM vulnerabilities remain limited, restricting effectiveness and applicability. To address this issue, we analyze the VAE and U-Net components of LDMs, revealing their vulnerabilities. Specifically, we study the response of U-Net to specific structural and frequency patterns in the latent space and find that it is susceptible to high-frequency and periodic latent features. Furthermore, we observe channel correlations during the VAE encoding process. Inspired by these, we propose QRShield, an efficient protection method that exploits the vulnerabilities of LDMs. By constructing high-frequency and periodic features consistent across latent channels and combining them with a momentum-based translation-invariant attack strategy, QRShield achieves stronger and more efficient protection. QRShield significantly improves protection performance in various fine-tuning settings, with over 10% gains in multiple metrics, a threefold increase in generation speed, and nearly 50% reduction in memory usage. Therefore, our work offers a more practical method to prevent AI art plagiarism.

Jiashuaizi Mo, Sang-Woon Jeon, Hua Wang, Xiangqi Chen, Yanchao Wang, Minglu Li, Zhonglong Zheng

Neural textures have emerged as pivotal assets in next-generation neural rendering pipelines. However, hardware limitations and programming interface constraints lead to suboptimal performance in multi-instance real-time rendering scenarios. This bottleneck becomes particularly acute for texture-intensive tasks such as font rendering. To address this, we propose Neural Outline Cache (NOC), a novel neural font texture supporting real-time anti-aliased rendering and procedural editing within modern neural graphics pipelines. NOC's lightweight network leverages multi-resolution hash encoding to cache spline-derived SDFs, delivering anti-aliased rendering via standard graphics pipelines. For massive-instance scalability, our cache buffer layout (CBL) and batch-fused inference (BFI), tailored for NOC, mitigate neural texture streaming bottlenecks. We constructed an evaluation dataset using five font styles. In offline rendering, our proposed method achieves overall average results of 57.35 dB PSNR, 0.998 SSIM, and 1.1584e-3 pixel RMSE, while maintaining approximately 0.5ms frame latency with 500 real-time instances. To demonstrate its versatility, we integrated a procedural editor for visual effects editing of NOC textures. These results all prove that NOC is a reliable, production-ready neural asset.

Xin Ming, Yuxuan Han, Tianyu Huang, Feng Xu

Reconstructing topologically consistent facial geometry is crucial for the digital avatar creation pipelines. Existing methods either require tedious manual efforts, lack generalization to in-the-wild data, or are constrained by the limited expressiveness of 3D Morphable Models. To address these limitations, we propose VGGTFace, an automatic approach that innovatively applies the 3D foundation model, i.e. VGGT, for topologically consistent facial geometry reconstruction from in-the-wild multi-view images captured by everyday users. Our key insight is that, by leveraging VGGT, our method naturally inherits strong generalization ability and expressive power from its large-scale training and point map representation. However, it is unclear how to reconstruct a topologically consistent mesh from VGGT, as the topology information is missing in its prediction. To this end, we augment VGGT with Pixel3DMM for injecting topology information via pixel-aligned UV values. In this manner, we convert the pixel-aligned point map of VGGT to a point cloud with topology. Tailored to this point cloud with known topology, we propose a novel Topology-Aware Bundle Adjustment strategy to fuse them, where we construct a Laplacian energy for the Bundle Adjustment objective. Our method achieves high-quality reconstruction in 10 seconds for 16 views on a single NVIDIA RTX 4090. Experiments demonstrate state-of-the-art results on benchmarks and impressive generalization to in-the-wild data.

Qi Ming, Liuqian Wang, Juan Fang, Xudong Zhao, Yucheng Xu, Ziyi Teng, Yue Zhou, Xiaoxi Hu, Xiaohan Zhang, Yufei Guo

Arbitrary-Oriented Object Detection (AOOD) has found broad applications in embodied intelligence, autonomous driving, and satellite remote sensing. However, current AOOD frameworks face challenges in ineffective feature extraction and orientation regression inaccuracy. Inspired by Hilbert curve's intrinsic locality-preserving property, we propose a flexible Hilbert curve-Encoded Rotation-Equivariant Oriented Object Detector (HERO-Det). Our innovations include: (i) a novel Hilbert curve traversal convolution paradigm with a dimensionality reduction scheme, which employs locality-preserving spatial filling curves for feature transformation, (ii) a Hilbert pyramid transformer enabling hierarchical construction of multi-scale feature sequences through space-folding operations, as well as (iii) an orientation-adaptive prediction head that decouples rotation-equivariant regression features from invariant classification cues to resolve orientation regression dilemmas in two-stage detectors. Extensive experiments show HERO-Det achieves state-of-the-art performance on AOOD benchmarks, with mAP of 79.56%, 90.64%, 90.10%, and 80.47% on DOTA, HRSC2016, SSDD, and HRSID, respectively. Performance gains in cross-task validation further demonstrate the versatility of our method to diverse vision tasks, such as medical image segmentation and 3D object detection.

Yu Miao, Juanjuan Zhao, Sijie Song, Ran Gong, Yuanqian Zhu, Lusha Qi, Yan Qiang

Data augmentation is an effective technique for regularizing deep networks, which helps to enhance the generalizability and robustness of the model. However, in the field of medical imaging, traditional data augmentation techniques such as cropping, rotation, and degradation may inadvertently alter the critical characteristics of pathological lesions. Conventional semantic augmentation methods, such as altering the color and contrast of the object background, may also affect the structural features of medical images in uncontrolled semantic directions. Such operational conditions compromise the model's diagnostic reliability in medical contexts. To address this issue, we propose a surprisingly efficient implicit augmentation-invariant learning strategy (AILS) via variational Bayesian inference on differentially constrained feature manifolds. Parameterizing probability measures over tangent space through deep networks enables precise estimation of semantic direction distributions. Subsequently, geodesic-aware semantic features are sampled from the reparameterized variational posterior, achieving semantic-consistent augmentation. Simultaneously, to mine augmentation distribution invariance, we design the AiHLoss, which constrains the augmentation distribution to facilitate the network to learn augmentation invariance. Extensive experiments demonstrate that AILS exhibits high performance on public medical image datasets, outperforming existing augmentation methods.

Pingyi Miao, Xianlai Chen, Kai Sun, Yunbo Wang, Shuang Zhao, Ying An

Foundational vision-language models (VLMs), such as CLIP, are emerging as a promising paradigm in vision tasks due to their strong generalization ability. Nevertheless, adapting them to downstream tasks remains challenging, especially in biomedical imaging, where scarce annotations, low-contrast features and complex patterns hinder model adaptation. Thus, prompt tuning is employed to facilitate the adaptation of VLMs. However, current prompt tuning methods like Context Optimization (CoOp) mainly learn a single yet static prompt which is applied to all images, and such one-size-fits-all prompt cannot describe the case-specific diagnostic cues in biomedical data, compromising the adaptation of VLMs. To this end, we propose a Dynamic Prompt Policy learning method that enables efficient adaptation of Biomedical VLMs (BioDPP) for accurate and highly generalizable few-shot biomedical image classification. Specifically, we conceptualize the learnable context as an agent, and present a paradigm of learning a dynamic prompting policy, rather than obtaining a single yet static prompt. Wherein, a dual-reward mechanism is developed to guide policy learning via the feedback on both classification decision and the consistency between the prompt and the context, steering the agent to generate context-aware prompts. Moreover, we devise adaptive baseline stabilization to dynamically regulate reward advantage value throughout the training process, enabling policy refinement in a complex reward space tailored to biomedical VLMs. Extensive experiments are conducted on 10 biomedical datasets, and the results reveal that our BioDPP achieves superior performance, demonstrating more efficient prompt optimization in biomedical VLMs.

Tuna Han Salih Meral, Hidir Yesiltepe, Connor Dunlop, Pinar Yanardag

Text-to-video models have demonstrated impressive capabilities in producing diverse video content, yet often lack fine-grained control over motion. We address the problem of motion transfer: given a source video and a target text prompt, generate a new video that preserves the source motion while matching the target semantics and allowing large changes in appearance and scene layout. We introduce MotionFlow, a training-free framework that performs test-time latent optimization guided by attention-derived motion cues. MotionFlow first extracts cross-attention maps from a pre-trained video diffusion model and converts them into spatio-temporal motion masks for the source subject. During generation, it optimizes the target latents so that their evolving attention patterns align with these masks, while the target text controls appearance. This avoids direct attention-map replacement and any model-specific fine-tuning, reducing artifacts and improving flexibility. Qualitative and quantitative experiments, including a user study, show that MotionFlow outperforms existing methods in motion fidelity, temporal consistency, and versatility, even under drastic scene changes.

Zhaorui Meng, Lu Yin, Yangqing Hou, Anjun Chen, Shihui Guo, Yipeng Qin

Sparse Inertial Measurement Units (IMUs) based human motion capture has gained significant momentum, driven by the adaptation of fundamental AI tools such as recurrent neural networks (RNNs) and transformers that are tailored for temporal and spatial modeling. Despite these achievements, current research predominantly focuses on pipeline and architectural designs, with comparatively little attention given to regularization methods, highlighting a critical gap in developing a comprehensive AI toolkit for this task. To bridge this gap, we propose motion label smoothing, a novel method that adapts the classic label smoothing strategy from classification to the sparse IMU-based motion capture task. Specifically, we first demonstrate that a naive adaptation of label smoothing, including simply blending a uniform vector or a "uniform" motion representation (e.g., dataset-average motion or a canonical T-pose), is suboptimal; and argue that a proper adaptation requires increasing the entropy of the smoothed labels. Second, we conduct a thorough analysis of human motion labels, identifying three critical properties: 1) Temporal Smoothness, 2) Joint Correlation, and 3) Low-Frequency Dominance, and show that conventional approaches to entropy enhancement (e.g., blending Gaussian noise) are ineffective as they disrupt these properties. Finally, we propose the blend of a novel skeleton-based Perlin noise for motion label smoothing, designed to raise label entropy while satisfying motion properties. Extensive experiments applying our motion label smoothing to three state-of-the-art methods across four real-world IMU datasets demonstrate its effectiveness and robust generalization (plug-and-play) capability.

Yucong Meng, Zhiwei Yang, Kexue Fu, Zhijian Song, Yonghong Shi

The challenge of accelerated MRI reconstruction lies in recovering high-quality images from undersampled k-space. Recently, the selective state space model (Mamba) has shown promising results in various tasks with balanced global receptive field and computational efficiency, shedding new light on MRI reconstruction. However, existing approaches directly flatten 2D images based on spatial positions and apply Mamba to vision tasks, failing to preserve and explore the content properties. In this paper, we posit that the key to unlocking Mamba's full potential for MRI reconstruction lies in content-aware sequence modeling. We investigate two fundamental challenges: (1) how to reasonably preserve semantic information when converting 2D images into 1D sequences, and (2) how to effectively identify and recover the crucial high-frequency textures. To this end, we introduce CAM, a novel framework that shifts Mamba-based MRI reconstruction from position-based to content-aware sequence modeling. Specifically, we introduce three modules: (1) the Semantic Preservation Scanning Module (SPSM) introduces learnable clustering centers to group similar pixels, establishing the semantic preserved sequence. (2) The Texture Extraction Scanning Module (TESM) acts as a differentiable local texture descriptor to estimate crucial high-frequency information, forming the texture emphasized sequence. (3) The Texture Enhancement Mamba Module (TEMM) further modulates the semantic sequence with texture-informed system matrices derived from the texture sequence, yielding both context- and texture-aware sequential representations. With these enhancements, CAM significantly outperforms existing methods across various datasets and under-sampling masks.

Xianhui Meng, Yukang Huo, Li Zhang, Liu Liu, Haonan Jiang, Yan Zhong, Pingrui Zhang, Cewu Lu, Jun Liu

Articulated objects are prevalent in daily life and robotic manipulation tasks. However, compared to rigid objects, pose tracking for articulated objects remains an underexplored problem due to their inherent kinematic constraints. To address these challenges, this work proposes a novel point-pair-based pose tracking framework, termed PPF-Tracker. The proposed framework first performs quasi-canonicalization of point clouds in the SE(3) Lie group space, and then models articulated objects using Point Pair Features (PPF) to predict pose voting parameters by leveraging the invariance properties of SE(3). Finally, semantic information of joint axes is incorporated to impose unified kinematic constraints across all parts of the articulated object. PPF-Tracker is systematically evaluated on both synthetic datasets and real-world scenarios, demonstrating strong generalization across diverse and challenging environments. Experimental results highlight the effectiveness and robustness of PPF-Tracker in multi-frame pose tracking of articulated objects. We believe this work can foster advances in robotics, embodied intelligence, and augmented reality.

Rang Meng, Yan Wang, Weipeng Wu, Ruobing Zheng, Yuming Li, Chenguang Ma

Recent work on human animation usually incorporates large-scale video models, thereby achieving more vivid performance. However, the practical use of such methods is hindered by the slow inference speed and high computational demands. Moreover, traditional work typically employs separate models for each animation task, increasing costs in multi-task scenarios and worsening the dilemma. To address these limitations, we introduce EchoMimicV3, an efficient framework that unifies multi-task and multi-modal human animation. At the core of EchoMimicV3 lies a threefold design: a Soup-of-Tasks paradigm, a Soup-of-Modals paradigm, and a novel training and inference strategy. The Soup-of-Tasks leverages multi-task mask inputs and a counter-intuitive task allocation strategy to achieve multi-task gains without multi-model pains. Meanwhile, the Soup-of-Modals introduces a Coupled-Decoupled Multi-Modal Cross Attention module to inject multi-modal conditions, complemented by a Timestep Phase-aware Multi-Modal Allocation mechanism to dynamically modulate multi-modal mixtures. Besides, we propose Negative Direct Preference Optimization and Phase-aware Negative Classifier-Free Guidance, which ensure stable training and inference. Extensive experiments and analyses demonstrate that EchoMimicV3, with a minimal model size of 1.3 billion parameters, achieves competitive performance in both quantitative and qualitative evaluations. We are committed to open-sourcing our code for community use.

Meng Meng, Zichang Tan, Yong Zhang, Xu Zhou

Text-video retrieval aims to bridge vision and language areas, which is a crucial task in multi-modal intelligence. The core idea is to learn video and textual features to quantify their semantic relevance. A common limitation in current approaches is the oversimplification of video content, where complex spatiotemporal structures are compressed into a single global representation. Consequently, these methods struggle to fully capture dynamic visual variations and discriminative appearance inside a video, further complicating cross-modal alignment. To alleviate these issues, we introduce a novel decoupling approach that independently processes appearance and motion cues, capitalizing on their complementary nature for more expressive video modeling. Specifically, we propose an appearance-motion decomposed network (AMD-Net) to decouple spatial-level appearance and temporal-level motion understanding via the discriminative appearance learning and multi-scale motion learning modules. The proposed model enjoys several merits. First, the designed discriminative appearance learning module with a Singular Value Decomposition (SVD) based prototype initialization can effectively reduce redundant appearance information, and a high-order cross-aggregation mechanism enhances prototype resilience and facilitates comprehensive video understanding. Second, the proposed multi-scale motion learning (MML) module can capture motion features at varying temporal scales, which are complementary to appearance features for accurate text-video retrieval. Extensive experiments on five standard benchmarks demonstrate that our method performs favorably against state-of-the-art methods.

Lingzhuang Meng, Mingwen Shao, Xiang Lv, Mengyao Wu, Yuanjian Qiao, Jie Zhang

Head avatar generation is facilitated to construct high-fidelity 3D virtual personas from a single portrait, but it also raises the risk of unauthorized personal avatars generation. Recent 2D portrait protection methods actively prevent malicious image generation by perturbing the identity features. However, there are two key limitations when directly applied to prevent 3D head avatar generation: 1) These methods neglect the inherent 3D geometric structure of portrait, thus failing to disrupt the modeling of 3D shapes or poses. 2) They focus only on identity offset and are unable to interfere with the overall appearance, resulting in excessive preservation of facial characteristics. To overcomes these limitations, we propose a 3D defense framework termed Anti-Avatar, tailored to protect against unauthorized 3D head avatar generation from a single portrait. Specifically, Anti-Avatar consists of two key designs: Geometric Disruption and Perceptual Confusion. The former disrupts the precise reconstruction of 3D structure by interfering with the estimation of geometric parameters, thus affecting the structural accuracy of the 3D avatar. Collaboratively, the latter confuses image features by dispersing attention distribution, thereby hindering the effective perception of portrait appearance. Benefiting from the above dual-space divergence in geometry and perception, the avatars generated by our protected portraits exhibit substantial discrepancies from the originals. Extensive experiments show that our Anti-Avatar outperforms 2D methods in protection performance and effectively resists reconstruction and manipulation by state-of-the-art 3D head avatar generation methods.

Jiayang Meng, Tao Huang, Hong Chen, Chen Hou, Guolong Zheng

Federated learning synchronizes models through gradient transmission and aggregation. However, these gradients pose significant privacy risks, as sensitive training data is embedded within them. Existing gradient inversion attacks suffer from significantly degraded reconstruction performance when gradients are perturbed by noise-a common defense mechanism. In this paper, we introduce gradient-guided conditional diffusion models for reconstructing private images from leaked gradients, without prior knowledge of the target data distribution. Our approach leverages the inherent denoising capability of diffusion models to circumvent the partial protection offered by noise perturbation, thereby improving attack performance under such defenses. We further provide a theoretical analysis of the reconstruction error bounds and the convergence properties of the attack loss, characterizing the impact of key factors—such as noise magnitude and attacked model architecture—on reconstruction quality. Extensive experiments demonstrate our attack's superior reconstruction performance with Gaussian noise-perturbed gradients, and confirm our theoretical findings.