arXiv subjects

Zehua Ma

Publications and source records attributed to Zehua Ma.

At least 19 recordsLinked to original sources

arXiv2026

Beyond the Eye: Efficient Multimodal Reasoning via Self-Regulated Implicit Visual Tools

Recent multimodal large language models (MLLMs) have made remarkable progress on fine-grained perception tasks under the "Thinking with Images" (TwI) paradigm by iteratively performing various visual tool operations. However, this paradigm relies heavily on frequent external tool calls and repeated image re-encoding, which leads to substantial computational overhead and inference latency. To address these issues, we propose Beyond the Eye (BEE), a novel implicit visual tool paradigm centered on self-regulated capability. BEE directly incorporates visual tool invocation behaviors into the training objective and encourages the model to develop a self-regulated invocation mechanism. This design enables the model to adaptively balance internal knowledge and implicit tools, avoiding redundant tool usage while substantially reducing inference latency. Specifically, BEE involves a two-stage training process: (1) Formalized Chain-of-Thought (CoT) Supervised Fine-tuning (SFT). We construct CoT trajectories with structured tool slots and mixed invocation states. This stage activates the model's implicit tool representations and adaptive switching capability. (2) Self-regulated Reward-Driven Alignment. To address redundant tool usage caused by ambiguous cognitive boundaries, we first introduce the Net Tool Gain (NTG) metric to quantify this phenomenon. Based on this observation, we further propose a self-regulated reward mechanism. This mechanism penalizes ineffective tool dependency and encourages the model to perform knowledge routing, ensuring that implicit tools are invoked only when the model's internal knowledge is insufficient. BEE achieves state-of-the-art performance in fine-grained visual perception while remaining competitive in general reasoning tasks and achieving substantial gains in inference efficiency.

cs.CV↗

arXiv2026

Flow of Truth: Proactive Temporal Forensics for Image-to-Video Generation

The rapid rise of image-to-video (I2V) generation enables realistic videos to be created from a single image but also brings new forensic demands. Unlike static images, I2V content evolves over time, requiring forensics to move beyond 2D pixel-level tampering localization toward tracing how pixels flow and transform throughout the video. As frames progress, embedded traces drift and deform, making traditional spatial forensics ineffective. To address this unexplored dimension, we present **Flow of Truth**, the first proactive framework focusing on temporal forensics in I2V generation. A key challenge lies in discovering a forensic signature that can evolve consistently with the generation process, which is inherently a creative transformation rather than a deterministic reconstruction. Despite this intrinsic difficulty, we innovatively redefine video generation as *the motion of pixels through time rather than the synthesis of frames*. Building on this view, we propose a learnable forensic template that follows pixel motion and a template-guided flow module that decouples motion from image content, enabling robust temporal tracing. Experiments show that Flow of Truth generalizes across commercial and open-source I2V models, substantially improving temporal forensics performance.

cs.CV↗

arXiv2026

AnyCrowd: Instance-Isolated Identity-Pose Binding for Arbitrary Multi-Character Animation

Controllable character animation has advanced rapidly in recent years, yet multi-character animation remains underexplored. As the number of characters grows, multi-character reference encoding becomes more susceptible to latent identity entanglement, resulting in identity bleeding and reduced controllability. Moreover, learning precise and spatio-temporally consistent correspondences between reference identities and driving pose sequences becomes increasingly challenging, often leading to identity-pose mis-binding and inconsistency in generated videos. To address these challenges, we propose AnyCrowd, a Diffusion Transformer (DiT)-based video generation framework capable of scaling to an arbitrary number of characters. Specifically, we first introduce an Instance-Isolated Latent Representation (IILR), which encodes character instances independently prior to DiT processing to prevent latent identity entanglement. Building on this disentangled representation, we further propose Tri-Stage Decoupled Attention (TSDA) to bind identities to driving poses by decomposing self-attention into: (i) instance-aware foreground attention, (ii) background-centric interaction, and (iii) global foreground-background coordination. Furthermore, to mitigate token ambiguity in overlapping regions, an Adaptive Gated Fusion (AGF) module is integrated within TSDA to predict identity-aware weights, effectively fusing competing token groups into identity-consistent representations...

cs.CV↗

arXiv2026

SKeDA: A Generative Watermarking Framework for Text-to-video Diffusion Models

The rise of text-to-video generation models has raised growing concerns over content authenticity, copyright protection, and malicious misuse. Watermarking serves as an effective mechanism for regulating such AI-generated content, where high fidelity and strong robustness are particularly critical. Recent generative image watermarking methods provide a promising foundation by leveraging watermark information and pseudo-random keys to control the initial sampling noise, enabling lossless embedding. However, directly extending these techniques to videos introduces two key limitations: Existing designs implicitly rely on strict alignment between video frames and frame-dependent pseudo-random binary sequences used for watermark encryption. Once this alignment is disrupted, subsequent watermark extraction becomes unreliable; and Video-specific distortions, such as inter-frame compression, significantly degrade watermark reliability. To address these issues, we propose SKeDA, a generative watermarking framework tailored for text-to-video diffusion models. SKeDA consists of two components: (1) Shuffle-Key-based Distribution-preserving Sampling (SKe) employs a single base pseudo-random binary sequence for watermark encryption and derives frame-level encryption sequences through permutation. This design transforms watermark extraction from synchronization-sensitive sequence decoding into permutation-tolerant set-level aggregation, substantially improving robustness against frame reordering and loss; and (2) Differential Attention (DA), which computes inter-frame differences and dynamically adjusts attention weights during extraction, enhancing robustness against temporal distortions. Extensive experiments demonstrate that SKeDA preserves high video generation quality and watermark robustness.

cs.CV↗

arXiv2026

ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting

Generating 3D content from a single image remains a fundamentally challenging and ill-posed problem due to the inherent absence of geometric and textural information in occluded regions. While state-of-the-art generative models can synthesize auxiliary views to provide additional supervision, these views inevitably contain geometric inconsistencies and textural misalignments that propagate and amplify artifacts during 3D reconstruction. To effectively harness these imperfect supervisory signals, we propose an adaptive optimization framework guided by excess risk decomposition, termed ERGO. Specifically, ERGO decomposes the optimization losses in 3D Gaussian splatting into two components, i.e., excess risk that quantifies the suboptimality gap between current and optimal parameters, and Bayes error that models the irreducible noise inherent in synthesized views. This decomposition enables ERGO to dynamically estimate the view-specific excess risk and adaptively adjust loss weights during optimization. Furthermore, we introduce geometry-aware and texture-aware objectives that complement the excess-risk-derived weighting mechanism, establishing a synergistic global-local optimization paradigm. Consequently, ERGO demonstrates robustness against supervision noise while consistently enhancing both geometric fidelity and textural quality of the reconstructed 3D content. Extensive experiments on the Google Scanned Objects dataset and the OmniObject3D dataset demonstrate the superiority of ERGO over existing state-of-the-art methods.

cs.CV↗

arXiv2026

Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiation

With the rising need for spatially grounded tasks such as Vision-Language Navigation/Action, allocentric perception capabilities in Vision-Language Models (VLMs) are receiving growing focus. However, VLMs remain brittle on allocentric spatial queries that require explicit perspective shifts, where the answer depends on reasoning in a target-centric frame rather than the observed camera view. Thus, we introduce Allocentric Perceiver, a training-free strategy that recovers metric 3D states from one or more images with off-the-shelf geometric experts, and then instantiates a query-conditioned allocentric reference frame aligned with the instruction's semantic intent. By deterministically transforming reconstructed geometry into the target frame and prompting the backbone VLM with structured, geometry-grounded representations, Allocentric Perceriver offloads mental rotation from implicit reasoning to explicit computation. We evaluate Allocentric Perciver across multiple backbone families on spatial reasoning benchmarks, observing consistent and substantial gains ($\sim$10%) on allocentric tasks while maintaining strong egocentric performance, and surpassing both spatial-perception-finetuned models and state-of-the-art open-source and proprietary models.

cs.CV↗

arXiv2026

FreeText: Training-Free Text Rendering in Diffusion Transformers via Attention Localization and Spectral Glyph Injection

Large-scale text-to-image (T2I) diffusion models excel at open-domain synthesis but still struggle with precise text rendering, especially for multi-line layouts, dense typography, and long-tailed scripts such as Chinese. Prior solutions typically require costly retraining or rigid external layout constraints, which can degrade aesthetics and limit flexibility. We propose \textbf{FreeText}, a training-free, plug-and-play framework that improves text rendering by exploiting intrinsic mechanisms of \emph{Diffusion Transformer (DiT)} models. \textbf{FreeText} decomposes the problem into \emph{where to write} and \emph{what to write}. For \emph{where to write}, we localize writing regions by reading token-wise spatial attribution from endogenous image-to-text attention, using sink-like tokens as stable spatial anchors and topology-aware refinement to produce high-confidence masks. For \emph{what to write}, we introduce Spectral-Modulated Glyph Injection (SGMI), which injects a noise-aligned glyph prior with frequency-domain band-pass modulation to strengthen glyph structure and suppress semantic leakage (rendering the concept instead of the word). Extensive experiments on Qwen-Image, FLUX.1-dev, and SD3 variants across longText-Benchmark, CVTG, and our CLT-Bench show consistent gains in text readability while largely preserving semantic alignment and aesthetic quality, with modest inference overhead.

cs.CV↗

arXiv2025

AuthSig: Safeguarding Scanned Signatures Against Unauthorized Reuse in Paperless Workflows

With the deepening trend of paperless workflows, signatures as a means of identity authentication are gradually shifting from traditional ink-on-paper to electronic formats.Despite the availability of dynamic pressure-sensitive and PKI-based digital signatures, static scanned signatures remain prevalent in practice due to their convenience. However, these static images, having almost lost their authentication attributes, cannot be reliably verified and are vulnerable to malicious copying and reuse. To address these issues, we propose AuthSig, a novel static electronic signature framework based on generative models and watermark, which binds authentication information to the signature image. Leveraging the human visual system's insensitivity to subtle style variations, AuthSig finely modulates style embeddings during generation to implicitly encode watermark bits-enforcing a One Signature, One Use policy.To overcome the scarcity of handwritten signature data and the limitations of traditional augmentation methods, we introduce a keypoint-driven data augmentation strategy that effectively enhances style diversity to support robust watermark embedding. Experimental results show that AuthSig achieves over 98% extraction accuracy under both digital-domain distortions and signature-specific degradations, and remains effective even in print-scan scenarios.

cs.CV↗

arXiv2025

LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation

The rapid progress of image-guided video generation (I2V) has raised concerns about its potential misuse in misinformation and fraud, underscoring the urgent need for effective digital watermarking. While existing watermarking methods demonstrate robustness within a single modality, they fail to trace source images in I2V settings. To address this gap, we introduce the concept of Robust Diffusion Distance, which measures the temporal persistence of watermark signals in generated videos. Building on this, we propose I2VWM, a cross-modal watermarking framework designed to enhance watermark robustness across time. I2VWM leverages a video-simulation noise layer during training and employs an optical-flow-based alignment module during inference. Experiments on both open-source and commercial I2V models demonstrate that I2VWM significantly improves robustness while maintaining imperceptibility, establishing a new paradigm for cross-modal watermarking in the era of generative video. \href{https://github.com/MrCrims/I2VWM-Robust-Watermarking-for-Image-to-Video-Generation}{Code Released.}

cs.CV↗

arXiv2025

LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

In controllable image synthesis, generating coherent and consistent images from multiple references with spatial layout awareness remains an open challenge. We present LAMIC, a Layout-Aware Multi-Image Composition framework that, for the first time, extends single-reference diffusion models to multi-reference scenarios in a training-free manner. Built upon the MMDiT model, LAMIC introduces two plug-and-play attention mechanisms: 1) Group Isolation Attention (GIA) to enhance entity disentanglement; and 2) Region-Modulated Attention (RMA) to enable layout-aware generation. To comprehensively evaluate model capabilities, we further introduce three metrics: 1) Inclusion Ratio (IN-R) and Fill Ratio (FI-R) for assessing layout control; and 2) Background Similarity (BG-S) for measuring background consistency. Extensive experiments show that LAMIC achieves state-of-the-art performance across most major metrics: it consistently outperforms existing multi-reference baselines in ID-S, BG-S, IN-R and AVG scores across all settings, and achieves the best DPG in complex composition tasks. These results demonstrate LAMIC's superior abilities in identity keeping, background preservation, layout control, and prompt-following, all achieved without any training or fine-tuning, showcasing strong zero-shot generalization ability. By inheriting the strengths of advanced single-reference models and enabling seamless extension to multi-image scenarios, LAMIC establishes a new training-free paradigm for controllable multi-image composition. As foundation models continue to evolve, LAMIC's performance is expected to scale accordingly. Our implementation is available at: https://github.com/Suchenl/LAMIC.

cs.CV↗

arXiv2025

TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity

AI-generated content (AIGC) enables efficient visual creation but raises copyright and authenticity risks. As a common technique for integrity verification and source tracing, digital image watermarking is regarded as a potential solution to above issues. However, the widespread adoption and advancing capabilities of generative image editing tools have amplified malicious tampering risks, while simultaneously posing new challenges to passive tampering detection and watermark robustness. To address these challenges, this paper proposes a Tamper-Aware Generative image WaterMarking method named TAG-WM. The proposed method comprises four key modules: a dual-mark joint sampling (DMJS) algorithm for embedding copyright and localization watermarks into the latent space while preserving generative quality, the watermark latent reconstruction (WLR) utilizing reversed DMJS, a dense variation region detector (DVRD) leveraging diffusion inversion sensitivity to identify tampered areas via statistical deviation analysis, and the tamper-aware decoding (TAD) guided by localization results. The experimental results demonstrate that TAG-WM achieves state-of-the-art performance in both tampering robustness and localization capability even under distortion, while preserving lossless generation quality and maintaining a watermark capacity of 256 bits. The code is available at: https://github.com/Suchenl/TAG-WM.

cs.MM↗

arXiv2024

CamLoPA: A Hidden Wireless Camera Localization Framework via Signal Propagation Path Analysis

Hidden wireless cameras pose significant privacy threats, necessitating effective detection and localization methods. However, existing solutions often require spacious activity areas, expensive specialized devices, or pre-collected training data, limiting their practical deployment. To address these limitations, we introduce CamLoPA, a training-free wireless camera detection and localization framework that operates with minimal activity space constraints using low-cost commercial-off-the-shelf (COTS) devices. CamLoPA can achieve detection and localization in just 45 seconds of user activities with a Raspberry Pi board. During this short period, it analyzes the causal relationship between the wireless traffic and user movement to detect the presence of a snooping camera. Upon detection, CamLoPA employs a novel azimuth location model based on wireless signal propagation path analysis. Specifically, this model leverages the time ratio of user paths crossing the First Fresnel Zone (FFZ) to determine the azimuth angle of the camera. Then CamLoPA refines the localization by identifying the camera's quadrant. We evaluate CamLoPA across various devices and environments, demonstrating that it achieves 95.37% snooping camera detection accuracy and an average localization error of 17.23, under the significantly reduced activity space requirements. Our demo are available at https://www.youtube.com/watch?v=GKam04FzeM4.

cs.CR↗

arXiv2024

DreamVTON: Customizing 3D Virtual Try-on with Personalized Diffusion Models

Image-based 3D Virtual Try-ON (VTON) aims to sculpt the 3D human according to person and clothes images, which is data-efficient (i.e., getting rid of expensive 3D data) but challenging. Recent text-to-3D methods achieve remarkable improvement in high-fidelity 3D human generation, demonstrating its potential for 3D virtual try-on. Inspired by the impressive success of personalized diffusion models (e.g., Dreambooth and LoRA) for 2D VTON, it is straightforward to achieve 3D VTON by integrating the personalization technique into the diffusion-based text-to-3D framework. However, employing the personalized module in a pre-trained diffusion model (e.g., StableDiffusion (SD)) would degrade the model's capability for multi-view or multi-domain synthesis, which is detrimental to the geometry and texture optimization guided by Score Distillation Sampling (SDS) loss. In this work, we propose a novel customizing 3D human try-on model, named \textbf{DreamVTON}, to separately optimize the geometry and texture of the 3D human. Specifically, a personalized SD with multi-concept LoRA is proposed to provide the generative prior about the specific person and clothes, while a Densepose-guided ControlNet is exploited to guarantee consistent prior about body pose across various camera views. Besides, to avoid the inconsistent multi-view priors from the personalized SD dominating the optimization, DreamVTON introduces a template-based optimization mechanism, which employs mask templates for geometry shape learning and normal/RGB templates for geometry/texture details learning. Furthermore, for the geometry optimization phase, DreamVTON integrates a normal-style LoRA into personalized SD to enhance normal map generative prior, facilitating smooth geometry modeling.

cs.CV↗

arXiv2024

SPSW: Database Watermarking Based on Fake Tuples and Sparse Priority Strategy

Databases play a crucial role in storing and managing vast amounts of data in various organizations and industries. Yet the risk of database leakage poses a significant threat to data privacy and security. To trace the source of database leakage, researchers have proposed many database watermarking schemes. Among them, fake-tuples-based database watermarking shows great potential as it does not modify the original data of the database, ensuring the seamless usability of the watermarked database. However, the existing fake-tuple-based database watermarking schemes need to insert a large number of fake tuples for the embedding of each watermark bit, resulting in low watermark transparency. Therefore, we propose a novel database watermarking scheme based on fake tuples and sparse priority strategy, named SPSW, which achieves the same watermark capacity with a lower number of inserted fake tuples compared to the existing embedding strategy. Specifically, for a database about to be watermarked, we prioritize embedding the sparsest watermark sequence, i.e., the sequence containing the most `0' bits among the currently available watermark sequences. For each bit in the sparse watermark sequence, when it is set to `1', SPSW will embed the corresponding set of fake tuples into the database. Otherwise, no modifications will be made to the database. Through theoretical analysis, the proposed sparse priority strategy not only improves transparency but also enhances the robustness of the watermark. The comparative experimental results with other database watermarking schemes further validate the superior performance of the proposed SPSW, aligning with the theoretical analysis.

cs.DB↗

arXiv2023

DeAR: A Deep-learning-based Audio Re-recording Resilient Watermarking

Audio watermarking is widely used for leaking source tracing. The robustness of the watermark determines the traceability of the algorithm. With the development of digital technology, audio re-recording (AR) has become an efficient and covert means to steal secrets. AR process could drastically destroy the watermark signal while preserving the original information. This puts forward a new requirement for audio watermarking at this stage, that is, to be robust to AR distortions. Unfortunately, none of the existing algorithms can effectively resist AR attacks due to the complexity of the AR process. To address this limitation, this paper proposes DeAR, a deep-learning-based audio re-recording resistant watermarking. Inspired by DNN-based image watermarking, we pioneer a deep learning framework for audio carriers, based on which the watermark signal can be effectively embedded and extracted. Meanwhile, in order to resist the AR attack, we delicately analyze the distortions that occurred in the AR process and design the corresponding distortion layer to cooperate with the proposed watermarking framework. Extensive experiments show that the proposed algorithm can resist not only common electronic channel distortions but also AR distortions. Under the premise of high-quality embedding (SNR=25.86dB), in the case of a common re-recording distance (20cm), the algorithm can effectively achieve an average bit recovery accuracy of 98.55%.

cs.SD↗

arXiv2023

OAcode: Overall Aesthetic 2D Barcode on Screen

Nowadays, two-dimensional (2D) barcodes have been widely used in various domains. And a series of aesthetic 2D barcode schemes have been proposed to improve the visual quality and readability of 2D barcodes for better integration with marketing materials. Yet we believe that the existing aesthetic 2D barcode schemes are partially aesthetic because they only beautify the data area but retain the position detection patterns with the blackwhite appearance of traditional 2D barcode schemes. Thus, in this paper, we propose the first overall aesthetic 2D barcode scheme, called OAcode, in which the position detection pattern is canceled. Its detection process is based on the pre-designed symmetrical data area of OAcode, whose symmetry could be used as the calibration signal to restore the perspective transformation in the barcode scanning process. Moreover, an enhanced demodulation method is proposed to resist the lens distortion common in the camera-shooting process. The experimental results illustrate that when 5$\times$5 cm OAcode is captured with a resolution of 720$\times$1280 pixels, at the screen-camera distance of 10 cm and the angle less or equal to 25°, OAcode has 100% detection rate and 99.5% demodulation accuracy. For 10$\times$10 cm OAcode, it could be extracted by consumer-grade mobile phones at a distance of 90 cm with around 90% accuracy.

cs.MM↗

arXiv2023

AnisoTag: 3D Printed Tag on 2D Surface via Reflection Anisotropy

In the past few years, the widespread use of 3D printing technology enables the growth of the market of 3D printed products. On Esty, a website focused on handmade items, hundreds of individual entrepreneurs are selling their 3D printed products. Inspired by the positive effects of machine-readable tags, like barcodes, on daily product marketing, we propose AnisoTag, a novel tagging method to encode data on the 2D surface of 3D printed objects based on reflection anisotropy. AnisoTag has an unobtrusive appearance and much lower extraction computational complexity, contributing to a lightweight low-cost tagging system for individual entrepreneurs. On AnisoTag, data are encoded by the proposed tool as reflective anisotropic microstructures, which would reflect distinct illumination patterns when irradiating by collimated laser. Based on it, we implement a real-time detection prototype with inexpensive hardware to determine the reflected illumination pattern and decode data according to their mapping. We evaluate AnisoTag with various 3D printer brands, filaments, and printing parameters, demonstrating its superior usability, accessibility, and reliability for practical usage.

cs.HC↗

arXiv2022

Go Wide or Go Deep: Levering Watermarking Performance with Computational Cost for Specific Images

Digital watermarking has been widely studied for the protection of intellectual property. Traditional watermarking schemes often design in a "wider" rule, which applies one general embedding mechanism to all images. But this will limit the scheme into a robustness-invisibility trade-off, where the improvements of robustness can only be achieved by the increase of embedding intensity thus causing the visual quality decay. However, a new scenario comes out at this stage that many businesses wish to give high level protection to specific valuable images, which requires high robustness and high visual quality at the same time. Such scenario makes the watermarking schemes should be designed in a "deeper" way which makes the embedding mechanism customized to specific images. To achieve so, we break the robustness-invisibility trade-off by introducing computation cost in, and propose a novel auto-decoder-like image-specified watermarking framework (ISMark). Based on ISMark, the strong robustness and high visual quality for specific images can be both achieved. In detail, we apply an optimization procedure (OPT) to replace the traditional embedding mechanism. Unlike existing schemes that embed watermarks using a learned encoder, OPT regards the cover image as the optimizable parameters to minimize the extraction error of the decoder, thus the features of each specified image can be effectively exploited to achieve superior performance. Extensive experiments indicate that ISMark outperforms the state-of-the-art methods by a large margin, which improves the average bit error rate by 4.64% (from 4.86% to 0.22%) and PSNR by 2.20dB (from 32.50dB to 34.70dB).

cs.CR↗