arXiv subjects

Chuanwei Huang

Publications and source records attributed to Chuanwei Huang.

13 recordsLinked to original sources

arXiv2026

Cascade Forgery Mining Network for Fingerprint Presentation Attack Detection

Fingerprint Presentation Attack Detection (PAD) is a critical component of fingerprint identification systems, serving as a protective measure against unauthorized access. In this paper, we observe that different regions of a fingerprint image can exhibit varying Artifact Extraction Difficulty (AED), with high-AED regions requiring more sophisticated extraction mechanisms to capture more subtle discriminative evidence. To address this issue, we propose to quantify AED using local Gabor feature certainty and partition fingerprint images into multiple regions based on their respective AED values. We then propose an AED guided Cascade Forgery Mining Network (CFM-Net) that employs an adaptive-depth feature extraction architecture to detect more precise and comprehensive artifact evidence across regions with heterogeneous AED values. Furthermore, we introduce an Orientation Guided Adversarial Training (OGAT) module to filter out identity information from PAD features while preserving the integrity of original artifact evidence. Experimental evaluations on LivDet datasets demonstrate the superior performance of our approach compared to state-of-the-art methods and achieve significant improvement in the classification ability of high AED fingerprints.

cs.CV↗

arXiv2026

Exploring Specular Reflection Inconsistency for Generalizable Face Forgery Detection

Detecting deepfakes has become increasingly challenging as forgery faces synthesized by AI-generated methods, particularly diffusion models, achieve unprecedented quality and resolution. Existing forgery detection approaches relying on spatial and frequency features demonstrate limited efficacy against high-quality, entirely synthesized forgeries. In this paper, we propose a novel detection method grounded in the observation that facial attributes governed by complex physical laws and multiple parameters are inherently difficult to replicate. Specifically, we focus on illumination, particularly the specular reflection component in the Phong illumination model, which poses the greatest replication challenge due to its parametric complexity and nonlinear formulation. We introduce a fast and accurate face texture estimation method based on Retinex theory to enable precise specular reflection separation. Furthermore, drawing from the mathematical formulation of specular reflection, we posit that forgery evidence manifests not only in the specular reflection itself but also in its relationship with corresponding face texture and direct light. To address this issue, we design the Specular-Reflection-Inconsistency-Network (SRI-Net), incorporating a two-stage cross-attention mechanism to capture these correlations and integrate specular reflection related features with image features for robust forgery detection. Experimental results demonstrate that our method achieves superior performance on both traditional deepfake datasets and generative deepfake datasets, particularly those containing diffusion-generated forgery faces.

cs.CV↗

arXiv2025

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets

Vision-language models (VLMs) often struggle with compositional reasoning due to insufficient high-quality image-text data. To tackle this challenge, we propose a novel block-based diffusion approach that automatically generates counterfactual datasets without manual annotation. Our method utilizes large language models to identify entities and their spatial relationships. It then independently generates image blocks as "puzzle pieces" coherently arranged according to specified compositional rules. This process creates diverse, high-fidelity counterfactual image-text pairs with precisely controlled variations. In addition, we introduce a specialized loss function that differentiates inter-set from intra-set samples, enhancing training efficiency and reducing the need for negative samples. Experiments demonstrate that fine-tuning VLMs with our counterfactual datasets significantly improves visual reasoning performance. Our approach achieves state-of-the-art results across multiple benchmarks while using substantially less training data than existing methods.

cs.CV↗

arXiv2025

From Imitation to Innovation: The Emergence of AI Unique Artistic Styles and the Challenge of Copyright Protection

Current legal frameworks consider AI-generated works eligible for copyright protection when they meet originality requirements and involve substantial human intellectual input. However, systematic legal standards and reliable evaluation methods for AI art copyrights are lacking. Through comprehensive analysis of legal precedents, we establish three essential criteria for determining distinctive artistic style: stylistic consistency, creative uniqueness, and expressive accuracy. To address these challenges, we introduce ArtBulb, an interpretable and quantifiable framework for AI art copyright judgment that combines a novel style description-based multimodal clustering method with multimodal large language models (MLLMs). We also present AICD, the first benchmark dataset for AI art copyright annotated by artists and legal experts. Experimental results demonstrate that ArtBulb outperforms existing models in both quantitative and qualitative evaluations. Our work aims to bridge the gap between the legal and technological communities and bring greater attention to the societal issue of AI art copyrights.

cs.CV↗

arXiv2025

Synthetic Data RL: Task Definition Is All You Need

Reinforcement learning (RL) is a powerful way to adapt foundation models to specialized tasks, but its reliance on large-scale human-labeled data limits broad adoption. We introduce Synthetic Data RL, a simple and general framework that reinforcement fine-tunes models using only synthetic data generated from a task definition. Our method first generates question and answer pairs from the task definition and retrieved documents, then adapts the difficulty of the question based on model solvability, and selects questions using the average pass rate of the model across samples for RL training. On Qwen-2.5-7B, our method achieves a 29.2% absolute improvement over the base model on GSM8K (+2.9 pp vs. instruction-tuned, +6.6 pp vs. Self-Instruct), 8.7% on MATH, 13.1% on GPQA (+7.0 pp vs. SynthLLM), 8.9% on MedQA, 17.7% on CQA (law) and 13.7% on CFA (finance). It surpasses supervised fine-tuning under the same data budget and nearly matches RL with full human data across datasets (e.g., +17.2 pp on GSM8K). Adding 100 human demonstrations improves the performance of GSM8K only by 0.4 pp, showing a limited added value. By reducing human data annotation, Synthetic Data RL enables scalable and efficient RL-based model adaptation. Code and demos are available at https://github.com/gydpku/Data_Synthesis_RL/.

cs.CL↗

arXiv2025

Control-CLIP: Decoupling Category and Style Guidance in CLIP for Specific-Domain Generation

Text-to-image diffusion models have shown remarkable capabilities of generating high-quality images closely aligned with textual inputs. However, the effectiveness of text guidance heavily relies on the CLIP text encoder, which is trained to pay more attention to general content but struggles to capture semantics in specific domains like styles. As a result, generation models tend to fail on prompts like "a photo of a cat in Pokemon style" in terms of simply producing images depicting "a photo of a cat". To fill this gap, we propose Control-CLIP, a novel decoupled CLIP fine-tuning framework that enables the CLIP model to learn the meaning of category and style in a complement manner. With specially designed fine-tuning tasks on minimal data and a modified cross-attention mechanism, Control-CLIP can precisely guide the diffusion model to a specific domain. Moreover, the parameters of the diffusion model remain unchanged at all, preserving the original generation performance and diversity. Experiments across multiple domains confirm the effectiveness of our approach, particularly highlighting its robust plug-and-play capability in generating content with various specific styles.

cs.CV↗

arXiv2025

Semantic to Structure: Learning Structural Representations for Infringement Detection

Structural information in images is crucial for aesthetic assessment, and it is widely recognized in the artistic field that imitating the structure of other works significantly infringes on creators' rights. The advancement of diffusion models has led to AI-generated content imitating artists' structural creations, yet effective detection methods are still lacking. In this paper, we define this phenomenon as "structural infringement" and propose a corresponding detection method. Additionally, we develop quantitative metrics and create manually annotated datasets for evaluation: the SIA dataset of synthesized data, and the SIR dataset of real data. Due to the current lack of datasets for structural infringement detection, we propose a new data synthesis strategy based on diffusion models and LLM, successfully training a structural infringement detection model. Experimental results show that our method can successfully detect structural infringements and achieve notable improvements on annotated test sets.

cs.CV↗

arXiv2024

Ultrahigh-temperature ferromagnetism in ultrathin insulating films with ripple-infinite-layer structure

Ferromagnetism and electrical insulation are often at odds, signifying an inherent trade off. The simultaneous optimization of both in one material, essential for advancing spintronics and topological electronics, necessitates the individual manipulation over various degrees of freedom of strongly correlated electrons. Here, by selective control of the spin exchange and Coulomb interactions, we report the achievement of SrFeO2 thin films with resistivity above 106 Ohm.cm and strong magnetization with Curie temperature extrapolated to be 1200 K. Robust ferromagnetism is obtained down to 1.0 nm thickness on substrate and 2.0 nm for freestanding films. Featuring an out of plane oriented ripple infinite layer structure, this ferromagnetic insulating phase is obtained through extensive reduction of as grown brownmillerite SrFeO2.5 films at high compressive strains. Pronounced spin Hall magnetoresistance signals up to 0.0026 is further demonstrated with a Pt Hall bar device. Our findings promise emerging spintronic and topological electronic functionalities harnessing spin dynamics with minimized power dissipations.

cond-mat.mtrl-sci↗

arXiv2024

UniVG: Towards UNIfied-modal Video Generation

Diffusion based video generation has received extensive attention and achieved considerable success within both the academic and industrial communities. However, current efforts are mainly concentrated on single-objective or single-task video generation, such as generation driven by text, by image, or by a combination of text and image. This cannot fully meet the needs of real-world application scenarios, as users are likely to input images and text conditions in a flexible manner, either individually or in combination. To address this, we propose a Unified-modal Video Genearation system that is capable of handling multiple video generation tasks across text and image modalities. To this end, we revisit the various video generation tasks within our system from the perspective of generative freedom, and classify them into high-freedom and low-freedom video generation categories. For high-freedom video generation, we employ Multi-condition Cross Attention to generate videos that align with the semantics of the input images or text. For low-freedom video generation, we introduce Biased Gaussian Noise to replace the pure random Gaussian Noise, which helps to better preserve the content of the input conditions. Our method achieves the lowest Fréchet Video Distance (FVD) on the public academic benchmark MSR-VTT, surpasses the current open-source methods in human evaluations, and is on par with the current close-source method Gen2. For more samples, visit https://univg-baidu.github.io.

cs.CV↗

arXiv2013

Periodic elastic nanodomains in ultrathin tetrogonal-like BiFeO3 films

We present a synchrotron grazing incidence x-ray diffraction analysis of the domain structure and polar symmetry of highly strained BiFeO3 thin films grown on LaAlO3 substrate. We revealed the existence of periodic elastic nanodomains in the pure tetragonal-like BFO ultrathin films down to a thickness of 6 nm. A unique shear strain accommodation mechanism is disclosed. We further demonstrated that the periodicity of the nanodomains increases with film thickness but deviates from the classical Kittel's square root law in ultrathin thickness regime (6 - 30 nm). Temperature-dependent experiments also reveal the disappearance of periodic modulation above 90C due to a MC-MA structural phase transition.

cond-mat.mtrl-sci↗

arXiv2012

Study of strain effect on in-plane polarization in epitaxial BiFeO3 thin films using planar electrodes

Epitaxial strain plays an important role in determining physical properties of perovskite ferroelectric oxide thin films. However, it is very challenging to directly measure properties such as polarization in ultrathin strained films using traditional sandwich capacitor devices, because of high leakage current. We employed a planar electrode device with different crystallographical orientations between electrodes along different electric field orientation to directly measure the in-plane polarization-electric field (P-E) hysteresis loops in fully strained thin films. At high misfit strains such as -4.4%, the pure Tetrogonal-like phase is obtained and its polarization vector is constrained to lie in the (010) plane with a significantly large in-plane component, ~44 μC/cm2. First-principle calculations are carried out in parallel, and provide a good agreement with the experimental results. Our results pave the way to design in-plane devices based on T-like BFO and the strategy proposed here can be expanded to study all other similar strained multiferroic ultrathin films.

cond-mat.mtrl-sci↗

arXiv2011

Nanoscale domains in strained epitaxial BiFeO3 thin Films on LaSrAlO4 Substrate

BiFeO3 thin films with various thicknesses were grown epitaxially on (001) LaSrAlO4 single crystal substrates using pulsed laser deposition. High resolution x-ray diffraction measurements revealed that a tetragonal-like phase with c-lattice constant ~4.65 Å is stabilized by a large misfit strain. Besides, a rhombohedral-like phase with c-lattice constant ~3.99 Å was also detected at film thickness of ~50 nm and above to relieve large misfit strains. In-plane piezoelectric force microscopy studies showed clear signals and self-assembled nanoscale stripe domain structure for the tetragonal-like regions. These findings suggest a complex picture of nanoscale domain patterns in BiFeO3 thin films subjected to large compressive strains.

cond-mat.mtrl-sci↗

arXiv2010

Low-Symmetry Monoclinic Phases and Polarization Rotation Path Mediated By Epitaxial Strain in Multiferroic BiFeO3 Thin Films

A morphotropic phase boundary driven by epitaxial strain has been observed in a lead-free multiferroic BiFeO3 thin films and the strain-driven phase transitions were widely reported to be iso-symmetric Cc-Cc ones by recent works. In this paper, we suggest that the tetragonal-like BiFeO3 phase identified in epitaxial films on (001) LaAlO3 single crystal substrates is monoclinic MC. This MC phase is different from MA type monoclinic phase reported in BiFeO3 films grown on low mismatch substrates, such as SrTiO3. This is confirmed not only by synchrotron x-ray studies but also by piezoresponse force microscopy measurements. The polarization vectors of the tetragonal-like phase lie in the (100) plane, not the (110) plane as previously reported. A phenomenological analysis was proposed to explain the formation of MC Phase. Such a low symmetry MC phase, with its linkage to MA phase and the multiphase coexistence open an avenue for large piezoelectric response in BiFeO3 films and shed light on a complete understanding towards possible polarization rotation paths and enhanced multiferroicity in BiFeO3 films mediated by epitaxial strain. This work may also aid the understanding of developing new lead-free strain-driven morphotropic phase boundary in other ferroic systems.

cond-mat.mtrl-sci↗