arXiv subjects

Dong Liu

Publications and source records attributed to Dong Liu.

At least 127 records · Page 7Linked to original sources

arXiv2025

Dual form Complementary Masking for Domain-Adaptive Image Segmentation

Recent works have correlated Masked Image Modeling (MIM) with consistency regularization in Unsupervised Domain Adaptation (UDA). However, they merely treat masking as a special form of deformation on the input images and neglect the theoretical analysis, which leads to a superficial understanding of masked reconstruction and insufficient exploitation of its potential in enhancing feature extraction and representation learning. In this paper, we reframe masked reconstruction as a sparse signal reconstruction problem and theoretically prove that the dual form of complementary masks possesses superior capabilities in extracting domain-agnostic image features. Based on this compelling insight, we propose MaskTwins, a simple yet effective UDA framework that integrates masked reconstruction directly into the main training pipeline. MaskTwins uncovers intrinsic structural patterns that persist across disparate domains by enforcing consistency between predictions of images masked in complementary ways, enabling domain generalization in an end-to-end manner. Extensive experiments verify the superiority of MaskTwins over baseline methods in natural and biological image segmentation. These results demonstrate the significant advantages of MaskTwins in extracting domain-invariant features without the need for separate pre-training, offering a new paradigm for domain-adaptive segmentation.

cs.CV↗

arXiv2025

Partition Map-Based Fast Block Partitioning for VVC Inter Coding

Among the new techniques of Versatile Video Coding (VVC), the quadtree with nested multi-type tree (QT+MTT) block structure yields significant coding gains by providing more flexible block partitioning patterns. However, the recursive partition search in the VVC encoder increases the encoder complexity substantially. To address this issue, we propose a partition map-based algorithm to pursue fast block partitioning in inter coding. Based on our previous work on partition map-based methods for intra coding, we analyze the characteristics of VVC inter coding, and thus improve the partition map by incorporating an MTT mask for early termination. Next, we develop a neural network that uses both spatial and temporal features to predict the partition map. It consists of several special designs including stacked top-down and bottom-up processing, quantization parameter modulation layers, and partitioning-adaptive warping. Furthermore, we present a dual-threshold decision scheme to achieve a fine-grained trade-off between complexity reduction and rate-distortion (RD) performance loss. The experimental results demonstrate that the proposed method achieves an average 51.30% encoding time saving with a 2.12% Bjontegaard Delta Bit Rate (BDBR) under the random access configuration.

eess.IV↗

arXiv2025

Unlocking Altermagnetism in Antiferromagnetic 2D Films via Adsorption

Altermagnets, characterized by zero net magnetization and momentum-dependent spin splitting, have recently garnered significant attention due to their potential applications in a variety of fields. Here, we propose a symmetry-engineering strategy to unlock altermagnetism in two dimensional (2D) antiferromagnetic systems via surface adsorption of atoms or molecules. By employing spin group theory, we systematically demonstrate that selectively breaking symmetry operations, specifically those protecting spin degeneracy in momentum space, enables the emergence of nonrelativistic spin-split electronic states. Meanwhile, preserving rotation or mirror symmetries connecting opposite sublattices ensures zero net magnetization. Through a comprehensive classification of all symmetry operations across 80 layer groups, we identify 63 antiferromagnetic spin point groups (SPGs) describing 2D materials and further isolate 15 groups that can host altermagnetic characteristics through surface adsorption. Exemplified with monolayer antiferromagnetic VPS_3 and MnPSe_3, we show that oxygen adsorption on VPS_3 and NH_3 adsorption on MnPSe_3 selectively disrupt PT symmetry while retaining the [C2||m] symmetry. This engineered symmetry reduction induces pronounced spin splitting in their band structures without spin-orbit coupling, as confirmed by first-principles calculations. Furthermore, adsorption energy analysis and thermal stability phase diagrams under varying coverage regimes reveal optimal configurations for experimental feasibility. Our work establishes a universal symmetry-engineering framework to expand the family of altermagnetic materials, offering a versatile pathway to tailor spin-split functionalities in two-dimensional antiferromagnets for advanced quantum applications.

cond-mat.mes-hall↗

arXiv2025

When Schrödinger Bridge Meets Real-World Image Dehazing with Unpaired Training

Recent advancements in unpaired dehazing, particularly those using GANs, show promising performance in processing real-world hazy images. However, these methods tend to face limitations due to the generator's limited transport mapping capability, which hinders the full exploitation of their effectiveness in unpaired training paradigms. To address these challenges, we propose DehazeSB, a novel unpaired dehazing framework based on the Schrödinger Bridge. By leveraging optimal transport (OT) theory, DehazeSB directly bridges the distributions between hazy and clear images. This enables optimal transport mappings from hazy to clear images in fewer steps, thereby generating high-quality results. To ensure the consistency of structural information and details in the restored images, we introduce detail-preserving regularization, which enforces pixel-level alignment between hazy inputs and dehazed outputs. Furthermore, we propose a novel prompt learning to leverage pre-trained CLIP models in distinguishing hazy images and clear ones, by learning a haze-aware vision-language alignment. Extensive experiments on multiple real-world datasets demonstrate our method's superiority. Code: https://github.com/ywxjm/DehazeSB.

cs.CV↗

arXiv2025

MK-Pose: Category-Level Object Pose Estimation via Multimodal-Based Keypoint Learning

Category-level object pose estimation, which predicts the pose of objects within a known category without prior knowledge of individual instances, is essential in applications like warehouse automation and manufacturing. Existing methods relying on RGB images or point cloud data often struggle with object occlusion and generalization across different instances and categories. This paper proposes a multimodal-based keypoint learning framework (MK-Pose) that integrates RGB images, point clouds, and category-level textual descriptions. The model uses a self-supervised keypoint detection module enhanced with attention-based query generation, soft heatmap matching and graph-based relational modeling. Additionally, a graph-enhanced feature fusion module is designed to integrate local geometric information and global context. MK-Pose is evaluated on CAMERA25 and REAL275 dataset, and is further tested for cross-dataset capability on HouseCat6D dataset. The results demonstrate that MK-Pose outperforms existing state-of-the-art methods in both IoU and average precision without shape priors. Codes will be released at \href{https://github.com/yangyifanYYF/MK-Pose}{https://github.com/yangyifanYYF/MK-Pose}.

cs.CV↗

arXiv2025

Latent Posterior-Mean Rectified Flow for Higher-Fidelity Perceptual Face Restoration

The Perception-Distortion tradeoff (PD-tradeoff) theory suggests that face restoration algorithms must balance perceptual quality and fidelity. To achieve minimal distortion while maintaining perfect perceptual quality, Posterior-Mean Rectified Flow (PMRF) proposes a flow based approach where source distribution is minimum distortion estimations. Although PMRF is shown to be effective, its pixel-space modeling approach limits its ability to align with human perception, where human perception is defined as how humans distinguish between two image distributions. In this work, we propose Latent-PMRF, which reformulates PMRF in the latent space of a variational autoencoder (VAE), facilitating better alignment with human perception during optimization. By defining the source distribution on latent representations of minimum distortion estimation, we bound the minimum distortion by the VAE's reconstruction error. Moreover, we reveal the design of VAE is crucial, and our proposed VAE significantly outperforms existing VAEs in both reconstruction and restoration. Extensive experiments on blind face restoration demonstrate the superiority of Latent-PMRF, offering an improved PD-tradeoff compared to existing methods, along with remarkable convergence efficiency, achieving a 5.79X speedup over PMRF in terms of FID. Our code will be available as open-source.

cs.CV↗

arXiv2025

StableCodec: Taming One-Step Diffusion for Extreme Image Compression

Diffusion-based image compression has shown remarkable potential for achieving ultra-low bitrate coding (less than 0.05 bits per pixel) with high realism, by leveraging the generative priors of large pre-trained text-to-image diffusion models. However, current approaches require a large number of denoising steps at the decoder to generate realistic results under extreme bitrate constraints, limiting their application in real-time compression scenarios. Additionally, these methods often sacrifice reconstruction fidelity, as diffusion models typically fail to guarantee pixel-level consistency. To address these challenges, we introduce StableCodec, which enables one-step diffusion for high-fidelity and high-realism extreme image compression with improved coding efficiency. To achieve ultra-low bitrates, we first develop an efficient Deep Compression Latent Codec to transmit a noisy latent representation for a single-step denoising process. We then propose a Dual-Branch Coding Structure, consisting of a pair of auxiliary encoder and decoder, to enhance reconstruction fidelity. Furthermore, we adopt end-to-end optimization with joint bitrate and pixel-level constraints. Extensive experiments on the CLIC 2020, DIV2K, and Kodak dataset demonstrate that StableCodec outperforms existing methods in terms of FID, KID and DISTS by a significant margin, even at bitrates as low as 0.005 bits per pixel, while maintaining strong fidelity. Additionally, StableCodec achieves inference speeds comparable to mainstream transform coding schemes. All source code are available at https://github.com/LuizScarlet/StableCodec.

eess.IV↗

arXiv2025

GroupTuner: Efficient Group-Aware Compiler Auto-Tuning

Modern compilers typically provide hundreds of options to optimize program performance, but users often cannot fully leverage them due to the huge number of options. While standard optimization combinations (e.g., -O3) provide reasonable defaults, they often fail to deliver near-peak performance across diverse programs and architectures. To address this challenge, compiler auto-tuning techniques have emerged to automate the discovery of improved option combinations. Existing techniques typically focus on identifying critical options and prioritizing them during the search to improve efficiency. However, due to limited tuning iterations, the resulting data is often sparse and noisy, making it highly challenging to accurately identify critical options. As a result, these algorithms are prone to being trapped in local optima. To address this limitation, we propose GroupTuner, a group-aware auto-tuning technique that directly applies localized mutation to coherent option groups based on historically best-performing combinations, thus avoiding explicitly identifying critical options. By forgoing the need to know precisely which options are most important, GroupTuner maximizes the use of existing performance data, ensuring more targeted exploration. Extensive experiments demonstrate that GroupTuner can efficiently discover competitive option combinations, achieving an average performance improvement of 12.39% over -O3 while requiring only 77.21% of the time compared to the random search algorithm, significantly outperforming state-of-the-art methods.

cs.SE↗

arXiv2025

Testing black holes in a perfect fluid dark matter environment using quasinormal modes

This research explores the quasinormal modes (QNMs) characteristics of charged black holes in a perfect fluid dark matter (PFDM) environment. Based on the Event Horizon Telescope (EHT) observations of the M87* black hole shadow, we implemented necessary constraints on the parameter space($a/M$,$λ/M$).We found that for lower values of the magnetic charge parameter, the effective range of the PFDM parameter is approximately between -0.2 and 0, while as the magnetic charge parameter increases, this effective range gradually extends toward more negative values. Then through sixth-order WKB method and time-domain method, we systematically analyzed the quasinormal oscillation spectra under scalar field and electromagnetic field perturbations. The results reveal that: the magnetic charge $a$ and PFDM parameters $λ$ modulate the effective potential barrier of black hole spacetime, profoundly influencing the response frequency and energy dissipation characteristics of external perturbations. The consistently negative imaginary part of QNMs across the entire physical parameter domain substantiates the dynamical stability of the investigated system. Moreover, we discovered differences in the parameter variation sensitivity between scalar field and electromagnetic field perturbations, providing a theoretical basis for distinguishing different field disturbances. These results not only unveil the modulation mechanisms of electromagnetic interactions and dark matter distribution on black hole spacetime structures but also offer potential observational evidence for future gravitational wave detection and black hole environment identification.

gr-qc↗

arXiv2025

Searching for topological semi-complete bandgap in elastic truss lattices

Gapless topological phases have attracted significant interest across both quantum and classical systems owing to their novel physics and promising applications. However, the search for ideal gapless topological nodes inside a clear bandgap is still lacking in elastic systems. The degenerate points are always hidden in the trivial bulk bands due to the intricate elastic modes involved. Here, we find a topological semi-complete bandgap in a three-dimensional elastic truss lattice by tuning a supporting rod, which exhibits a complete bandgap except for the inevitable topological degenerate points. Furthermore, we experimentally map the topological semi-complete bandgap and the inside nontrivial surface state arcs with a scanning laser vibrometer. The introduced scheme provides a systematic approach for the idealization of semi-complete bandgaps and thus may significantly advance the practical utility of topological phases in mechanical engineering domains.

cond-mat.mes-hall↗

arXiv2025

NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution

This paper reviews the NTIRE 2025 RAW Image Restoration and Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Restoration and Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. The goal of this challenge is two fold, (i) restore RAW images with blur and noise degradations, (ii) upscale RAW Bayer images by 2x, considering unknown noise and blur. In the challenge, a total of 230 participants registered, and 45 submitted results during thee challenge period. This report presents the current state-of-the-art in RAW Restoration.

eess.IV↗

arXiv2025

Quasinormal Modes of Schwarzschild Black Holes in the Dehnen-(1, 4, 5/2) Type Dark Matter Halos

The Dehnen - type dark matter density distribution model is mainly used for dwarf galaxies. In recent years, researchers have speculated that black holes may exist in this dark matter model and have given the black hole metric solutions. On this basis, this paper conducts a systematic study on the quasinormal modes of a Schwarzschild black hole in a Dehnen - (1,4, 5/2) dark matter halo, revealing the influences of dark matter distribution and perturbation field types on the black hole's quasinormal modes.The research uses the shadow radius data of the M87$^{\ast}$ black hole. Through the geodesic equation, two sets of dark matter halo parameter values of $ρ_{\rm s}$ and $r_{\rm s}$ are determined, and the specific numerical values of the black hole's event horizon radius, photon sphere radius, and shadow radius under the corresponding conditions are obtained. The wave equations and effective potentials of the black hole under the perturbations of the scalar field, electromagnetic field, and axial gravitational were analyzed. It was found that the larger the values of $ρ_{\rm s}$ or $r_{\rm s}$, the smaller the peak value of the effective potential, and the wave function oscillation slows down with a lower frequency. The black hole remains stable under perturbations. These studies provide relevant data for the quasinormal modes of the Schwarzschild black hole in the Dehnen-(1,4, 5/2) type dark matter halo. They also offer crucial evidence for understanding the interaction mechanism between the black hole and the dark matter halo.

gr-qc↗

arXiv2025

Neural Video Compression with Context Modulation

Efficient video coding is highly dependent on exploiting the temporal redundancy, which is usually achieved by extracting and leveraging the temporal context in the emerging conditional coding-based neural video codec (NVC). Although the latest NVC has achieved remarkable progress in improving the compression performance, the inherent temporal context propagation mechanism lacks the ability to sufficiently leverage the reference information, limiting further improvement. In this paper, we address the limitation by modulating the temporal context with the reference frame in two steps. Specifically, we first propose the flow orientation to mine the inter-correlation between the reference frame and prediction frame for generating the additional oriented temporal context. Moreover, we introduce the context compensation to leverage the oriented context to modulate the propagated temporal context generated from the propagated reference feature. Through the synergy mechanism and decoupling loss supervision, the irrelevant propagated information can be effectively eliminated to ensure better context modeling. Experimental results demonstrate that our codec achieves on average 22.7% bitrate reduction over the advanced traditional video codec H.266/VVC, and offers an average 10.1% bitrate saving over the previous state-of-the-art NVC DCVC-FM. The code is available at https://github.com/Austin4USTC/DCMVC.

eess.IV↗

arXiv2025

CHRIS: Clothed Human Reconstruction with Side View Consistency

Creating a realistic clothed human from a single-view RGB image is crucial for applications like mixed reality and filmmaking. Despite some progress in recent years, mainstream methods often fail to fully utilize side-view information, as the input single-view image contains front-view information only. This leads to globally unrealistic topology and local surface inconsistency in side views. To address these, we introduce Clothed Human Reconstruction with Side View Consistency, namely CHRIS, which consists of 1) A Side-View Normal Discriminator that enhances global visual reasonability by distinguishing the generated side-view normals from the ground truth ones; 2) A Multi-to-One Gradient Computation (M2O) that ensures local surface consistency. M2O calculates the gradient of a sampling point by integrating the gradients of the nearby points, effectively acting as a smooth operation. Experimental results demonstrate that CHRIS achieves state-of-the-art performance on public benchmarks and outperforms the prior work.

cs.CV↗

arXiv2025

Augmented Deep Contexts for Spatially Embedded Video Coding

Most Neural Video Codecs (NVCs) only employ temporal references to generate temporal-only contexts and latent prior. These temporal-only NVCs fail to handle large motions or emerging objects due to limited contexts and misaligned latent prior. To relieve the limitations, we propose a Spatially Embedded Video Codec (SEVC), in which the low-resolution video is compressed for spatial references. Firstly, our SEVC leverages both spatial and temporal references to generate augmented motion vectors and hybrid spatial-temporal contexts. Secondly, to address the misalignment issue in latent prior and enrich the prior information, we introduce a spatial-guided latent prior augmented by multiple temporal latent representations. At last, we design a joint spatial-temporal optimization to learn quality-adaptive bit allocation for spatial references, further boosting rate-distortion performance. Experimental results show that our SEVC effectively alleviates the limitations in handling large motions or emerging objects, and also reduces 11.9% more bitrate than the previous state-of-the-art NVC while providing an additional low-resolution bitstream. Our code and model are available at https://github.com/EsakaK/SEVC.

eess.IV↗

arXiv2025

MT2ST: Adaptive Multi-Task to Single-Task Learning

Efficient machine learning (ML) has become increasingly important as models grow larger and data volumes expand. In this work, we address the trade-off between generalization in multi-task learning (MTL) and precision in single-task learning (STL) by introducing the Multi-Task to Single-Task (MT2ST) framework. MT2ST is designed to enhance training efficiency and accuracy in multi-modal tasks, showcasing its value as a practical application of efficient ML.

cs.LG↗

arXiv2025

Physics-Driven Neural Compensation For Electrical Impedance Tomography

Electrical Impedance Tomography (EIT) provides a non-invasive, portable imaging modality with significant potential in medical and industrial applications. Despite its advantages, EIT encounters two primary challenges: the ill-posed nature of its inverse problem and the spatially variable, location-dependent sensitivity distribution. Traditional model-based methods mitigate ill-posedness through regularization but overlook sensitivity variability, while supervised deep learning approaches require extensive training data and lack generalization. Recent developments in neural fields have introduced implicit regularization techniques for image reconstruction, but these methods typically neglect the physical principles underlying EIT, thus limiting their effectiveness. In this study, we propose PhyNC (Physics-driven Neural Compensation), an unsupervised deep learning framework that incorporates the physical principles of EIT. PhyNC addresses both the ill-posed inverse problem and the sensitivity distribution by dynamically allocating neural representational capacity to regions with lower sensitivity, ensuring accurate and balanced conductivity reconstructions. Extensive evaluations on both simulated and experimental data demonstrate that PhyNC outperforms existing methods in terms of detail preservation and artifact resistance, particularly in low-sensitivity regions. Our approach enhances the robustness of EIT reconstructions and provides a flexible framework that can be adapted to other imaging modalities with similar challenges.

eess.IV↗

arXiv2025

Learning Switchable Priors for Neural Image Compression

Neural image compression (NIC) usually adopts a predefined family of probabilistic distributions as the prior of the latent variables, and meanwhile relies on entropy models to estimate the parameters for the probabilistic family. More complex probabilistic distributions may fit the latent variables more accurately, but also incur higher complexity of the entropy models, limiting their practical value. To address this dilemma, we propose a solution to decouple the entropy model complexity from the prior distributions. We use a finite set of trainable priors that correspond to samples of the parametric probabilistic distributions. We train the entropy model to predict the index of the appropriate prior within the set, rather than the specific parameters. Switching between the trained priors further enables us to embrace a skip mode into the prior set, which simply omits a latent variable during the entropy coding. To demonstrate the practical value of our solution, we present a lightweight NIC model, namely FastNIC, together with the learning of switchable priors. FastNIC obtains a better trade-off between compression efficiency and computational complexity for neural image compression. We also implanted the switchable priors into state-of-the-art NIC models and observed improved compression efficiency with a significant reduction of entropy coding complexity.

cs.MM↗