arXiv subjects

Kai-Lung Hua

Publications and source records attributed to Kai-Lung Hua.

8 recordsLinked to original sources

arXiv2026

GeoMAD: Geometry-Aware Multi-View Anomaly Detection via Deformable Fusion and Distributional Alignment

Multi-view anomaly detection (MvAD) detects defects by exploiting complementary observations from multiple camera viewpoints. The central challenge is to fuse views with sufficient geometric awareness while remaining scalable to multi-class industrial settings. Existing methods typically fall into two extremes: voxel-based fusion provides explicit geometric alignment but requires costly 3D construction and class-specific assumptions, whereas lightweight patch-based fusion is efficient but relies on discrete candidate matching and lacks continuous cross-view correspondence. In this paper, we propose GeoMAD, a unified multi-view, multi-class AD framework that addresses both geometric correspondence deficiency and distributional inconsistency. Our \textit{Cross-view Deformable Fusion Module} (CDFM) learns content-adaptive, view-pair-specific sampling offsets directly on 2D feature maps and arranges them across a multi-scale window pyramid with image-global reference sampling, enabling hierarchical cross-view correspondence without camera calibration, voxel construction, or class-specific 3D supervision. We further introduce \textit{Distributional View Alignment} (DVA), a self-supervised cross-view regularization loss that aligns each view's bottleneck distribution against a per-instance view-centric target, enforcing global consistency without pixel-level correspondence. Together, CDFM and DVA bridge local geometric correspondence and global distributional consistency, providing geometry-aware and distribution-consistent fusion while preserving the efficiency of 2D feature-space learning. Extensive experiments on Real-IAD and MANTA-Tiny show that GeoMAD achieves strong detection and localization performance in unified MvAD.

cs.CV↗

arXiv2026

See More, Detect Less? Taming Information Leakage in Multi-View Anomaly Detection

In multi-view anomaly detection, more cross-view information can actually hurt. When multiple inspection views are naively fused in a reconstruction-based pipeline, normal cues from intact views propagate to the decoder, which faithfully reconstructs anomalous regions, collapsing the reconstruction gap the detector depends on. We call this failure mode \emph{cross-view information leakage} and show that effective multi-view fusion must explicitly restrict the information reaching the decoder. Building on this insight, we present GLAD(Global-Local Attention Driven framework), the first framework combining vision foundation model features with local and global cross-view fusion for multi-view anomaly detection. The Multi-view Merging Attention (MMA) module performs local cross-view fusion at linear complexity with learnable view importance weighting and token-wise gating, letting each view selectively incorporate fine-grained evidence from other views at $\mathcal{O}(N)$ cost. The Object-Guided Attention (OGA) module captures global context by aggregating class tokens from all views into a single object-level representation and broadcasting it back to patch tokens via temperature-scaled sigmoid gating, replacing the original patch representations rather than adding a residual to preserve the reconstruction gap. Experiments on Real-IAD and MANTA-Tiny show that GLAD outperforms state-of-the-art methods across sample-, image-, and pixel-level metrics, confirming that principled information restriction is key to multi-view anomaly reasoning.

cs.CV↗

arXiv2025

DirectDrag: High-Fidelity, Mask-Free, Prompt-Free Drag-based Image Editing via Readout-Guided Feature Alignment

Drag-based image editing using generative models provides intuitive control over image structures. However, existing methods rely heavily on manually provided masks and textual prompts to preserve semantic fidelity and motion precision. Removing these constraints creates a fundamental trade-off: visual artifacts without masks and poor spatial control without prompts. To address these limitations, we propose DirectDrag, a novel mask- and prompt-free editing framework. DirectDrag enables precise and efficient manipulation with minimal user input while maintaining high image fidelity and accurate point alignment. DirectDrag introduces two key innovations. First, we design an Auto Soft Mask Generation module that intelligently infers editable regions from point displacement, automatically localizing deformation along movement paths while preserving contextual integrity through the generative model's inherent capacity. Second, we develop a Readout-Guided Feature Alignment mechanism that leverages intermediate diffusion activations to maintain structural consistency during point-based edits, substantially improving visual fidelity. Despite operating without manual mask or prompt, DirectDrag achieves superior image quality compared to existing methods while maintaining competitive drag accuracy. Extensive experiments on DragBench and real-world scenarios demonstrate the effectiveness and practicality of DirectDrag for high-quality, interactive image manipulation. Project Page: https://frakw.github.io/DirectDrag/. Code is available at: https://github.com/frakw/DirectDrag.

cs.CV↗

arXiv2025

ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detection

The increasing realism of AI-generated images has raised serious concerns about misinformation and privacy violations, highlighting the urgent need for accurate and interpretable detection methods. While existing approaches have made progress, most rely on binary classification without explanations or depend heavily on supervised fine-tuning, resulting in limited generalization. In this paper, we propose ThinkFake, a novel reasoning-based and generalizable framework for AI-generated image detection. Our method leverages a Multimodal Large Language Model (MLLM) equipped with a forgery reasoning prompt and is trained using Group Relative Policy Optimization (GRPO) reinforcement learning with carefully designed reward functions. This design enables the model to perform step-by-step reasoning and produce interpretable, structured outputs. We further introduce a structured detection pipeline to enhance reasoning quality and adaptability. Extensive experiments show that ThinkFake outperforms state-of-the-art methods on the GenImage benchmark and demonstrates strong zero-shot generalization on the challenging LOKI benchmark. These results validate our framework's effectiveness and robustness. Code will be released upon acceptance.

cs.CV↗

arXiv2025

Neuro-MSBG: An End-to-End Neural Model for Hearing Loss Simulation

Hearing loss simulation models are essential for hearing aid deployment. However, existing models have high computational complexity and latency, which limits real-time applications and lack direct integration with speech processing systems. To address these issues, we propose Neuro-MSBG, a lightweight end-to-end model with a personalized audiogram encoder for effective time-frequency modeling. Experiments show that Neuro-MSBG supports parallel inference and retains the intelligibility and perceptual quality of the original MSBG, with a Spearman's rank correlation coefficient (SRCC) of 0.9247 for Short-Time Objective Intelligibility (STOI) and 0.8671 for Perceptual Evaluation of Speech Quality (PESQ). Neuro-MSBG reduces simulation runtime by a factor of 46 (from 0.970 seconds to 0.021 seconds for a 1 second input), further demonstrating its efficiency and practicality.

cs.SD↗

arXiv2025

Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model

Generative models have enabled the creation of highly realistic facial-synthetic images, raising significant concerns due to their potential for misuse. Despite rapid advancements in the field of deepfake detection, developing efficient approaches to leverage foundation models for improved generalizability to unseen forgery samples remains challenging. To address this challenge, we propose a novel side-network-based decoder that extracts spatial and temporal cues using the CLIP image encoder for generalized video-based Deepfake detection. Additionally, we introduce Facial Component Guidance (FCG) to enhance spatial learning generalizability by encouraging the model to focus on key facial regions. By leveraging the generic features of a vision-language foundation model, our approach demonstrates promising generalizability on challenging Deepfake datasets while also exhibiting superiority in training data efficiency, parameter efficiency, and model robustness.

cs.CV↗

arXiv2024

PixMamba: Leveraging State Space Models in a Dual-Level Architecture for Underwater Image Enhancement

Underwater Image Enhancement (UIE) is critical for marine research and exploration but hindered by complex color distortions and severe blurring. Recent deep learning-based methods have achieved remarkable results, yet these methods struggle with high computational costs and insufficient global modeling, resulting in locally under- or over- adjusted regions. We present PixMamba, a novel architecture, designed to overcome these challenges by leveraging State Space Models (SSMs) for efficient global dependency modeling. Unlike convolutional neural networks (CNNs) with limited receptive fields and transformer networks with high computational costs, PixMamba efficiently captures global contextual information while maintaining computational efficiency. Our dual-level strategy features the patch-level Efficient Mamba Net (EMNet) for reconstructing enhanced image feature and the pixel-level PixMamba Net (PixNet) to ensure fine-grained feature capturing and global consistency of enhanced image that were previously difficult to obtain. PixMamba achieves state-of-the-art performance across various underwater image datasets and delivers visually superior results. Code is available at: https://github.com/weitunglin/pixmamba.

cs.CV↗

arXiv2019

Using Deep Learning Neural Networks and Candlestick Chart Representation to Predict Stock Market

Stock market prediction is still a challenging problem because there are many factors effect to the stock market price such as company news and performance, industry performance, investor sentiment, social media sentiment and economic factors. This work explores the predictability in the stock market using Deep Convolutional Network and candlestick charts. The outcome is utilized to design a decision support framework that can be used by traders to provide suggested indications of future stock price direction. We perform this work using various types of neural networks like convolutional neural network, residual network and visual geometry group network. From stock market historical data, we converted it to candlestick charts. Finally, these candlestick charts will be feed as input for training a Convolutional Neural Network model. This Convolutional Neural Network model will help us to analyze the patterns inside the candlestick chart and predict the future movements of stock market. The effectiveness of our method is evaluated in stock market prediction with a promising results 92.2% and 92.1% accuracy for Taiwan and Indonesian stock market dataset respectively. The constructed model have been implemented as a web-based system freely available at http://140.138.155.216/deepcandle/ for predicting stock market using candlestick chart and deep learning neural networks.

q-fin.GN↗