JPEG, as a widely used image compression standard, often introduces severe visual artifacts when achieving high compression ratios. Although existing deep learning-based restoration methods have made considerable progress, they often struggle to recover complex texture details, resulting in over-smoothed outputs. To overcome these limitations, we propose SODiff, a novel and efficient semantic-oriented one-step diffusion model for JPEG artifacts removal. Our core idea is that effective restoration hinges on providing semantic-oriented guidance to the pre-trained diffusion model, thereby fully leveraging its powerful generative prior. To this end, SODiff incorporates a semantic-aligned image prompt extractor (SAIPE). SAIPE extracts rich features from low-quality (LQ) images and projects them into an embedding space semantically aligned with that of the text encoder. Simultaneously, it preserves crucial information for faithful reconstruction. Furthermore, we propose a quality factor-aware time predictor that implicitly learns the compression quality factor (QF) of the LQ image and adaptively selects the optimal denoising start timestep for the diffusion process. Extensive experimental results show that our SODiff outperforms recent leading methods in both visual quality and quantitative metrics.

Human-centered images often suffer from severe generic degradation during transmission and are prone to human motion blur (HMB), making restoration challenging. Existing research lacks sufficient focus on these issues, as both problems often coexist in practice. To address this, we design a degradation pipeline that simulates the coexistence of HMB and generic noise, generating synthetic degraded data to train our proposed HAODiff, a human-aware one-step diffusion. Specifically, we propose a triple-branch dual-prompt guidance (DPG), which leverages high-quality images, residual noise (LQ minus HQ), and HMB segmentation masks as training targets. It produces a positive–negative prompt pair for classifier‑free guidance (CFG) in a single diffusion step. The resulting adaptive dual prompts let HAODiff exploit CFG more effectively, boosting robustness against diverse degradations. For fair evaluation, we introduce MPII‑Test, a benchmark rich in combined noise and HMB cases. Extensive experiments show that our HAODiff surpasses existing state-of-the-art (SOTA) methods in terms of both quantitative metrics and visual quality on synthetic and real-world datasets, including our introduced MPII-Test. Code is available at: https://github.com/gobunu/HAODiff.

Multi-view clustering, which identifies shared semantics from different perspectives and classifies data samples into distinct categories using unsupervised methods, is gaining increasing interest. This task primarily focuses on learning consistent multi-view feature representations and clustering labels. Current approaches for achieving consistent multi-view feature representations often use techniques such as cascading, weight fusion, and attention mechanism fusion. These methods reconstruct features based on original low-level features via encoder-decoder, which often contain visual private information, leading to misleading feature representations. Furthermore, in the clustering label learning process, many methods use a two-stage approach: first, they achieve consistent feature representations, and then they apply hard labeling methods like K-means or spectral clustering to obtain clustering labels. Single-stage methods typically derive consistent labels through a linear coding layer based on consistent representation learning. These methods do not fully utilize the multi-view view semantic information, and consistent representation learning may be impaired when some low-quality views are present, leading to the generation of inaccurate semantic labels. To address these issues, we propose a Self-supervised Semantic Soft Label Learning Network for Deep Multi-view Clustering. Specifically, we introduce a consensus high-level feature learning module that uses a shared MLP layer to transform low-level features into a high-level feature space. To enhance the consistency between high-level features from different views, we maximize mutual information between these features and introduce the U-Projection module, which improves the expressive power of the consensus feature via resampling the features and concatenating the fused features before and after sampling operations. Additionally, we propose a self-supervised semantic label learning module that employs a dual-branch approach to independently learn consistent view-specific semantic labels through contrastive learning, while deriving view-consensus semantic labels from shared high-level features extracted from multiple views. Finally, KL divergence is used to align the view-consensus labels with the view-specific labels. A series of extensive experiments have shown that our approach yields superior clustering results compared to existing techniques.