Reversible Data Hiding in Shared Images (RDHSI) has emerged as a vital technique for secure distributed multimedia cloud computing applications. It can embed secret messages into shared images through Secret Sharing (SS) among multiple data hiders, which can be efficient for distributed systems with multiple participants. Recently, RDHSI has been adapted for Anonymous Submission Application Frameworks (ASAF) to facilitate secure multi-reviewer processes. However, existing schemes suffer from two critical limitations: 1) they predominantly support simple binary voting (e.g., “Yes” or “No”), failing to accommodate comprehensive reviews that require both numerical scores and textual comments; and 2) they distribute identity-related shares directly to reviewers, creating vulnerability to collusion attacks where reviewers can jointly reconstruct the applicant’s identity. To address these challenges, we propose a novel Essential RDHSI-based Anonymous Multiparty Review Framework (ER-AMRF). Unlike conventional threshold-based approaches, ER-AMRF leverages Essential Secret Sharing (ESS) to decouple the Applicant’s identity from the Reviewers’ shares, ensuring that identity recovery is cryptographically bound to a specific essential share and immune to Reviewer collusion. Specifically, we design a two-phase polynomial-based secret sharing scheme where detailed review results-comprising both comments and scores-are generated into review shares and subsequently embedded by multiple Reviewers into the shared images. At the receiver side, Lagrange interpolation is employed to extract the full review feedback from a sufficient number of marked images. Experimental results demonstrate that ER-AMRF achieves an embedding rate of up to 4 bits per pixel (bpp), outperforming state-of-the-art RDHSI schemes by 0.5 bpp while guaranteeing robust anonymity and data integrity.
Large-scale image transmission in Internet of Things (IoT) and multimedia networks requires more attack-resistant encryption. Existing chaotic image cryptosystems suffer from fixed evolutionary rhythms, insufficient keystream dynamics, and dynamical degradation during dimensional expansion. To address these issues, this paper proposes a cross-modal variable-step image encryption algorithm (CMVS-IE) driven by a topology-expandable discrete memristive bi-neuron cyclic neural network (DMBCNN) and piano-score features. Memristors act as both electromagnetic-radiation channels and inter-neuron synapses, enabling arbitrary-dimensional expansion, controllable grid and spatial multistability, and wide-range amplitude modulation. During encryption, the pitch, octave, and duration features of Melody of the Night 5 are combined with plaintext-associated factors to initialize the keystream, guide adaptive routing scrambling, and control three-dimensional spiral variable-step diffusion. Hardware experiments and NIST tests verify the feasibility and randomness of the chaotic source. CMVS-IE achieves an information entropy of 7.9993, a number of pixels change rate (NPCR) of 99.6093%, and a unified average changing intensity (UACI) of 33.4639%, while substantially reducing adjacent-pixel correlation. By combining scalable memristive dynamics with external score-driven control, CMVS-IE provides a viable approach to nonstationary image encryption and cross-modal multimedia security.
Infrared small target detection (IRSTD) is of great importance in both military and civilian applications, yet it remains highly challenging due to complex background clutter, weak target signatures, and the semantic discrepancy between shallow and deep features in encoder-decoder architectures. To address these issues, we propose PCFNet, an encoder-decoder network that incorporates pulse-coupled filtering into skip connections and introduces a cross-feature attention enhancement mechanism. Specifically, the proposed dynamic-threshold pulse-coupled filtering (DT-PCF) module suppresses background interference and enhances target saliency through learnable threshold dynamics and neighborhood coupling. In addition, the cross-feature attention enhancement (CFAE) module alleviates the semantic gap between shallow spatial details and deep semantic representations by performing deep-feature-guided cross-layer channel attention. Extensive experiments on three public benchmarks, NUAA-SIRST, NUDT-SIRST, and IRSTD-1K, demonstrate that PCFNet achieves state-of-the-art performance on multiple evaluation metrics. Ablation studies further verify the effectiveness of each proposed component, while complexity analysis shows that PCFNet provides a favorable trade-off between detection accuracy and model efficiency. Our code is available at: https://github.com/P-ZYang/PCFNet.
Unsupervised domain adaptation (UDA) semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Hierarchical domain shifts at data, feature, and semantic levels are challenging for UDA, and existing methods usually address the discrepancies from just one level. In this paper, a Hierarchical Structural Prototype-guided Consistency Learning framework (HSPC) is proposed to jointly tackle domain discrepancy. Specifically, for the data level, uncertainty-aware cross-domain consistency (UCDC) is designed. Through adaptive cross-domain supervision allocation, uncertain target regions are exploited as informative supervision signals. At the feature level, masked structure consistency learning (MSCL) is designed. Thus, prediction consistency is enforced under content-aware structured corruption, encouraging the model to capture robust and transferable structure cues. At the semantic level, dual-domain structure prototype-guided alignment (DSPA) is developed. By maintaining source and target prototype memories, class-wise feature distributions are progressively aligned and global semantic geometry is preserved. Extensive experiments on GTA to Cityscapes and SYNTHIA to Cityscapes demonstrate that HSPC achieves best performance across different backbones. Ablation studies further verify complementary effective-ness of UCDC, MSCL, and DSPA.
Daytime and nighttime haze degradation share atmospheric scattering induced commonality while exhibiting significant domain shifts caused by differences in illumination mechanisms and imaging conditions. Constrained by the assumption of a single illumination condition, existing dehazing methods struggle to simultaneously model the degradation patterns shared across daytime and nighttime scenes as well as the discrepancies induced by varying illumination conditions within a unified framework. To address this limitation, a two-stage framework, termed CDPformer, is proposed for unified day-night image dehazing. In the first stage, CLIP is fine-tuned with different textual labels to learn a cross day-night common haze prompt and a day-night differential degradation prompt, thereby providing the unified dehazing model with conditional cues that contain both common constraints and discrepancy-aware guidance. In the second stage, a prompt-driven U-shaped Transformer is proposed, in which a dual-CLIP prompt fusion module (DCPFM) and a prompt injection module (PIM) are introduced to promote effective alignment of the two prompt types and their interaction with network features. In addition, a learnable prompt (LP) is incorporated to further capture high-level and implicit latent degradation patterns, thereby providing effective degradation cues for the restoration network. Extensive experiments demonstrate that CDPformer achieves robust and consistent dehazing performance across both daytime and nighttime scenes, validating the effectiveness of the proposed two-stage unified modeling strategy and the collaborative guidance of multiple prompt types.
Stereo matching plays a crucial role in depth perception for autonomous vehicles. However, existing iterative approaches often incur high computational costs owing to redundant iterations, which fundamentally restricts their real-time applicability. To address this issue, we propose Context-Stereo-I, a lightweight iterative framework that reduces the number of iterations while enriching the hidden state with enhanced contextual and geometric information. Central to our approach is a Context-Guided Geometry Volume (CGV), constructed through gated interaction between a context-enhanced encoder and the decoder during cost aggregation. The CGV provides accurate initial disparity estimates and reliable matching cues for iterative refinement. Inside CGV, we propose a Gated Skip Connection (GSC) mechanism to improve information propagation from the encoder to decoder, effectively delivering more informative low-level features compared to standard skip connections. These low-level features are enhanced with contextual information via our proposed Enhanced Context Fusion (ECF) module. By integrating context-aware geometric cues into the iterative updater, Context-Stereo-I achieves outstanding performance in challenging regions and exhibits strong generalization in unseen scenarios. It ranks first on the KITTI 2012 and 2015 benchmarks among all published real-time methods, achieving a 3px-all error of 1.66% and a D1-all error of 1.73%, while running at 41 ms on an RTX 3080 GPU. Moreover, it demonstrates superior cross-domain generalization on both public datasets and real-world data compared to other real-time stereo matching approaches. Code is available at https://github.com/shidifen12/Context-Stereo.
Blind image deblurring remains a fundamental yet highly ill-posed problem in computer vision. Existing methods that rely on composite regularizations often lack a unified physical formulation, and thus struggle to balance structural preservation with fine-scale texture smoothing. Moreover, insufficient prior constraints on the kernel render these algorithms vulnerable to the larger-kernel effect, thus severely degrading performance when the kernel size is over-specified. To address these limitations, we propose novel image and kernel priors that derive from the inherent physical properties of clear images and ideal kernels. First, we introduce a flexible bimodal graph prior (FBP) that is based on graph signal processing. The FBP not only provides strong discrimination between sharp and blurred images but also flexibly promotes salient edge selection by enforcing a bimodal distribution of edge weights, which accurately recovers intermediate skeleton images. Subsequently, we reveal the inherent anisotropy in the patch distributions of ideal kernels via directional patch matching. On the basis of this crucial observation, we propose a discriminative kernel prior (DKP) with a clear physical interpretation. The DKP explicitly suppresses isotropic noise during kernel estimation, thereby robustly mitigating the larger-kernel effect and significantly increasing the tolerance of the algorithm to kernel size. Furthermore, we prove that the FBP can be well-approximated by the reweighted graph Laplacian (RGL) and derive an efficient alternating optimization scheme with closed-form solutions. The results of extensive experiments demonstrate that our method outperforms state-of-the-art algorithms on both synthetic and real-world datasets and exhibits superior efficacy in handling large-scale motion blur and defocus blur.
Contrastive Language-Image Pre-training (CLIP) has recently been explored for image-level weakly supervised semantic segmentation (WSSS) due to its semantic localization priors. However, CLIP is trained with global image-text alignment and lacks pixel-level discriminative supervision, making its category responses vulnerable to co-occurring non-target activations and confusion among semantically similar classes. Instead of merely refining visual response maps, this paper revisits CLIP-based WSSS from the perspective of text-prototype bias. We find that class text prototypes used for vision-text matching are jointly affected by instance-level co-occurrence semantics and category-level semantic coupling, which degrades response purity and inter-class separability. To this end, we propose TPD-CLIP, a text-prototype debiasing framework that calibrates biased class prototypes before vision-text matching to generate cleaner and more discriminative localization responses. TPD-CLIP consists of a Confusion-aware Semantic Decoupling Module (CSDM) and a Pairwise Semantic Confusion Matrix (PCM). CSDM leverages foreground and non-target region semantics to enhance target-semantic alignment while suppressing non-target interference. PCM further estimates asymmetric inter-class interference and adaptively modulates the separation strength for highly confusing negative categories. Experiments on PASCAL VOC 2012 and MS COCO 2014 showfinal that TPD-CLIP improves response quality, pseudo-label reliability, and final segmentation performance. Our code is available at https://github.com/jocka-weilen/TPD-CLIP.
The talking head generation task synthesizes videos from a single portrait image and audio input, animating the portrait to deliver the speech content. Non-autoregressive (NAR) approaches for talking head generation have demonstrated impressive quality and generation speeds by producing video frames in parallel, thereby overcoming the error accumulation problems inherent in frame-wise autoregressive (AR) methods. However, NAR methods have limited practical applicability due to prohibitive VRAM requirements, especially when generating long sequences (≥ 1000 frames) at high resolution (512 × 512). This paper proposes a novel framework that enables high-quality, non-autoregressive talking head generation while significantly reducing computational resource demands for both training and inference. We enhance efficiency through our Multi-stage Dynamics Compression Framework (MDCF), a two-stage pipeline that achieves a 768× compression ratio for pixel-level dynamics representations. Additionally, we demonstrate that this two-stage architecture cannot be effectively optimized via standard end-to-end training. We therefore introduce a Two-Phase Cascaded (TPC) training strategy to stably optimize the MDCF while effectively alleviating error accumulation during multi-stage compression. Experimental results demonstrate that our framework can non-autoregressively generate talking head videos with over 1600 frames at up to 512 × 512 resolution on a 16GB GPU, with state-of-the-art quality and inference speed. Our approach represents a significant advancement toward practical, resource-efficient talking head synthesis for real-world applications. The source code in the supplementary material will be publicly available.
Cross domain semantic segmentation faces significant challenges due to domain shift and the high cost of manual annotation. To address this problem, transfer learning has emerged as a key solution and it helps cross domain semantic segmentation by two manners. The first one is feature-level alignment by self-training or extracting domain invariant features, but the performance is limited by noisy pseudo label. The other is image translation-assisted approaches, which suffer from unsatisfactory translation results and the ignorance of potential semantic hidden features. Moreover, the synergistic relationship between transfer learning and semantic segmentation remains underexplored in existing methods, while the complementarity of feature-level and image-level alignment has received scarce attention. Hence, a novel end-to-end progressive co-training network (PCN) is proposed to overcome these shortcomings. Firstly, feature-level alignment branch and image translation branch both generate pseudo predictions and ensembled results are acquired, self-supervised learning and adversarial learning are utilized respectively. In order to ensure high-quality translation, semantic decoder and class center alignment module effectively consider class-wise visual consistency, while discrete wavelet transform further ensures sound structural details. Moreover, to facilitate the co-training of high-quality segmentation and nice transfer learning, a pseudo label refinement module is proposed by considering probability, information entropy and prediction consistency. Exhaustive experiments on ISPRS 2D Semantic Labeling Contest Dataset demonstrate the superiority of the PCN. The code will be available at https://github.com/lixinghua5540/PCN.
Text-to-image (T2I) generation has emerged as a crucial component of AI content generation, enabling the automatic creation of visual content from natural language descriptions. Within this rapidly evolving domain, evaluating whether a generated image and the associated text prompt are semantically aligned remains a significant challenge. The existing methods typically adopt implicit and holistic representations derived from pre-trained vision-language models, which fails to adequately explore semantic entities and their relationships in both visual and textual modalities. Motivated by the above facts, this paper presents Graph-Align, a novel graph-based T2I alignment evaluation model, which transforms T2I alignment into a graph matching problem. Specifically, a generated image and the corresponding text prompt are first represented as graph structures comprising nodes (entities) and edges (relations). Based upon the graph representations, two modules are designed to achieve fine-grained graph matching: Graph Fusion (GF) and Subgraph Search (SS). GF establishes latent semantic connections between visual and textual graphs. Then, SS searches the visual graph space to identify prompt-relevant subgraph regions. Finally, a T2I alignment score is obtained by calculating the similarity between the identified visual subgraphs and textual graphs. Extensive experiments and comparisons on three benchmark T2I alignment databases demonstrate the advantage of the proposed model. Codes are available at https://github.com/yzc-ippl/GraphAlign.
Reversible data hiding in shared images (RDHSI) has attracted increasing attention since it can improve the fault-tolerance and meanwhile provide conveniences for the shared image management. The existing RDHSI frameworks can be classified into internal embedding and external embedding. The former conducts image sharing with data embedding, which can provide the fault-tolerance for them. The latter only shares the original image and embeds the additional data into the shared images. However, there has not been a feasible method combining the advantages above two so far. To address this issue, we propose a novel RDHSI method, which is compatible with internal and external embedding, and possesses the advantages of those two frameworks. Thus, the proposed method has extensive applications. Specifically, a pixel is decomposed into two values whose 7 LSBs are both Hamming codes, yielding three crucial properties. The decomposed values are regarded as the coefficients to construct polynomials for (k, n)-threshold image sharing. Our data embedding has two phases, the internal one performs image sharing with data embedding to generate n marked shared images, and the external one further embeds the additional data into each marked shared image to generate a shared stego image using bit replacement. The receiver can extract the additional data from a shared stego image. When receiving any k shared stego images, all the candidates of replaced bits are traversed to reconstruct the polynomials. The original image as well as secret data can be revealed according to three properties. Theoretical analysis and experimental results demonstrate the proposed method outperforms some RDHSI methods.
Transformers have become essential for RGBT tracking because of their strong global modeling ability, but their attention patterns across layers and modalities are often highly similar, causing redundant computation and low tracking efficiency. To address this issue, we propose AALTrack, an efficient RGBT tracker based on Alternating Attention Learning, which exploits cross-layer and cross-modal attention correlations to reduce computation while preserving reliable attention prediction. Specifically, a lightweight attention prediction module uses historical attention priors to predict current-layer attention and replace redundant self-attention. To improve prediction reliability, these modules are inserted alternately into the RGB and TIR tracking backbones: when one modality predicts attention at a selected layer, the other retains full self-attention and provides a reliable reference for refinement through cross-modal attention propagation. We further introduce a dual knowledge distillation module, where predicted attention is supervised by teacher attention maps and feature-level distillation maintains stable feature representations. This design adds no inference overhead and improves prediction robustness. Extensive experiments on three RGBT tracking benchmarks show that AALTrack significantly accelerates inference while preserving tracking accuracy.
Transformer-Mamba hybrid models, which alternate between attention and state-space model (SSM) layers, have shown outstanding potential in image super-resolution (SR) by fully leveraging the strengths of both. However, existing hybrid models still suffer from the mismatch between Mamba’s inherent causality and the non-causal nature of 2D images. Besides, their heterogeneous operations and complex computational flows hinder efficient deployment on edge platforms. In this paper, we propose an algorithm-hardware co-optimized framework to accelerate lightweight hybrid SR models on edge devices. For algorithm design, we introduce MattenSR, a lightweight Transformer-Mamba hybrid SR model that alternately captures complementary local-global contextual information. As the key component of MattenSR, a novel Global-Aware State-Space Duality Module (GASM) is developed to eliminate Mamba’s causality without sequential scans, enhancing the global modeling capability for SR. For hardware optimization, we design a unified computing array and a reconfigurable base-2 approximation nonlinear unit to support diverse operations with high hardware utilization. To further reduce memory consumption and processing latency, a window-based streamlined (WinStream) dataflow is proposed, which unifies window partitioning and fine-grained pipeline scheduling for both attention and SSM. Finally, the overall hardware accelerator is developed and implemented on the Intel Stratix 10GX platform. Experimental results show that our MattenSR, with only 39K parameters, achieves better visual perception than other baselines. Moreover, compared to prior accelerators, our design achieves up to 27.3× and 7.7× improvements in throughput and energy efficiency, respectively.
Vision–language models such as CLIP provide semantically grounded priors for Unsupervised Domain Adaptation (UDA) in classification. However, existing CLIP-based UDA methods mainly adapt the model through the final-layer global visual embedding, leaving hierarchical representations in intermediate layers largely under-explored. Simply aggregating multi-level features is not a reliable solution for UDA, because shallow and mid-level representations are more sensitive to domain-specific appearance statistics and may introduce biased drift into both feature adaptation and pseudo-label learning. In this paper, we propose Multi-Level Representation Adaptation (MLRA), a CLIP-based UDA framework that exploits hierarchical visual representations while preserving the pretrained semantics of CLIP. Specifically, we introduce a Hierarchical Visual Aggregation (HVA) module to extract and adapt intermediate representations from multiple depths of the frozen CLIP visual encoder, and a Dual Anchoring Mechanism (DAM) to stabilize adaptation in both feature space and logit space. In the feature space, feature anchoring uses the original global CLIP feature as a semantic anchor to bound the HVA-induced residual update, thereby constraining representation drift while preserving CLIP’s pretrained semantic geometry. In the logit space, teacher logits computed from the original CLIP global feature regularize how the anchored visual feature is projected into the same fixed zero-shot class-text embedding space, thereby stabilizing pseudo-label learning and the resulting decision boundary. In this way, MLRA exploits transferable cross-layer cues while preserving CLIP’s pretrained semantic structure under domain shift. Experimental results on four UDA benchmarks show that MLRA achieves superior performance over existing state-of-the-art approaches.
Video Temporal Grounding is a fine-grained video understanding task that requires a nuanced alignment between linguistic semantics and dynamic visual content. However, existing approaches, ranging from global sentence-level to local phrase-level alignments, typically disregard the distinct semantic roles of word-level concepts. To address this, we propose the Hierarchical Concept Matching Network (HCMNet), a framework that explicitly disentangles and hierarchically integrates structured semantic concepts. Specifically, we design an Object Concept Matcher to establish entity-level correspondences using noun-based object cues. Subsequently, we design an Action Concept Matcher, which employs an action-aware cross-attention and a temporal self-attention to capture motion continuity and precise temporal transitions guided by action dynamics. By synergizing these specialized matchers, our framework achieves fine-grained semantic alignment and precise temporal localization, effectively bridging the gap between linguistic roles and visual evolution. Extensive experiments on QVHighlights, Charades-STA, and TACoS benchmarks demonstrate that HCMNet achieves state-of-the-art performance, confirming the superiority of our concept-guided paradigm.
Visible-infrared person re-identification (VI-ReID) aims to retrieve the same pedestrian across heterogeneous cameras, yet the substantial discrepancies between RGB and infrared images in illumination, texture, and spectral distributions severely limit the performance of existing methods. Although several recent studies have explored frequency-domain cues, how to jointly reduce input-level spectral discrepancy and feature-level modality bias remains insufficiently investigated. To address this issue, we propose a Frequency-Aware Cross-Modal Compensation Network, termed FAC-Net, for visible-infrared person reidentification. Specifically, we introduce a parameter-free Fourier style augmentation module at the input stage, which adaptively mixes low-frequency amplitude spectra to reduce cross-modal energy discrepancy at the source while preserving high-frequency information that maintains identity-related structures. During feature extraction, we design a dual-branch architecture consisting of a modality-invariant stream and a modality-compensation stream, and employ per-modality parameterization and an attention mechanism to finely correct statistical biases in the feature space. Furthermore, to mitigate gradient oscillations caused by cross-stream interactions, we adopt a task-specific safely-gated late fusion design with a zero-start mechanism, encouraging a gradual transition from independent learning to cross-stream collaboration. Extensive experiments on SYSU-MM01, RegDB, and LLCM show that the proposed method achieves competitive performance, with particularly strong Rank-1 accuracy across challenging cross-modal settings. The code will be made available at: https://github.com/ykding666/FACNet.
Scaling diffusion-based video generation to high spatial resolutions remains a significant computational bottleneck, as existing super-resolution methods either suffer from domain mismatches in pixel space or incur heavy sampling costs through iterative diffusion refinement. To address this, we introduce a lightweight latent upscaling framework that decouples resolution enhancement from stochastic generation, enabling scalable video synthesis with minimal overhead. Operating as a deterministic post-denoising transformation, the framework centers on a compact Causal Latent Upscaler (CLU) that incorporates a VAE-aware causal attention mechanism to preserve temporal coherence during spatial expansion. To bridge the gap between latent-space alignment and decoded visual fidelity, we further propose a progressive three-stage training strategy that transitions from efficient latent supervision to precise pixel-level refinement. Extensive experiments across real-world datasets and multiple text-to-video backbones demonstrate that our approach consistently enhances spatial resolution and perceptual quality while introducing negligible computational cost. By functioning as a plug-and-play module in latent space, the proposed framework offers a highly scalable and efficient pathway to high-definition video generation without modifying pretrained diffusion pipelines.
Hyperspectral image (HSI) and light detection and ranging (LiDAR) data provide complementary spectral and structural information, which are highly beneficial for land-cover classification. Despite recent progress, two fundamental challenges remain. First, most approaches mainly focus on spatial-domain feature modeling during single-modality enhancement, while the discriminative information embedded in the frequency domain is insufficiently explored. Second, cross-modal fusion lacks explicit amplitude–phase interaction in the frequency domain and does not leverage center semantic cues to guide the fusion process. To address these issues, this paper proposes a multi-scale Spatial–Frequency Cooperative Network (SFCM-Net) with Center-Modulated Fusion for Hyperspectral–LiDAR Classification. Specifically, a Spatial–Frequency Cooperative Enhancement (SFCE) block is designed to jointly model modality-specific features in both spatial and frequency domains, enabling more discriminative feature representations. Furthermore, a Center-Modulated Frequency Fusion (CMFF) block is developed to model amplitude–phase interactions and perform center-aware semantic modulation. The module enhances structural consistency in target regions, thereby improving classification performance. Experimental evaluations conducted on three public datasets verify the effectiveness of the proposed approach, which delivers improved performance compared with existing advanced methods. The code will be released at https://github.com/MSFLabX/SFCM-Net.
Over 29,568 children are reported missing in 2024 only in the United States, requiring reliable age-progressed imagery with natural expressions for effective search and recovery. However, existing diffusion models face fundamental limitations: expression-only methods cannot adjust age; age-only methods lack expression control. The core challenge is achieving simultaneous control over identity, age, and expression while preserving the pretrained backbone’s contextual generation capabilities. We propose DiffAgeX, a unified diffusion framework bridging backbone adaptation with stability for multi-attribute control. Our approach integrates two novel components: (1) Identity-CLIP Age-Aware (ICAA) module, featuring an offline variance-based layer selection strategy (ASEE) that identifies age-sensitive encoder layers and fuses identity, semantic, and age embeddings through learnable composition; (2) Adaptive Residual Fusion (ARF) mechanism, featuring bidirectional cross-attention that models identity-age-expression interactions, MLP-based perchannel scaling that fuses residuals based on mutual compatibility, and gradient-bounded damping that imposes a local bound on backbone and reduces backbone drift while preserving learned priors. Comprehensive evaluations demonstrate balanced performance across identity preservation, expression transfer, and age control. Across all reported evaluations, DiffAgeX achieves 84–88% expression accuracy, 0.25–0.31 identity distance, and 1.82–2.25 years target-age error. It enables coherent multi-attribute control with identity preservation, highlighting its potential for missing-person reconstruction, forensic analysis, and personalized avatar creation. For code, please refer to the GitHub repository: https://github.com/MSAfganUSTC/DiffAgeX.
