BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives
BLARM通过混合潜在刚性运动基元，从单目视频中生成3D物体动画，解决了高维顶点运动预测问题。
0 citationsRead paper
Selected work
Representative Papers
A Blueprint for Collaborative Cybersecurity Operations Centres with Capacity for Shared Situational Awareness, Coordinated Response, and Joint Preparedness
This study addresses the current lack of interoperable cybersecurity operations center architectures capable of supporting cross-border collaboration, shared situational awareness, and joint response—capabilities essential for critical service providers and national entities during large-scale cyber incidents. To bridge this gap, the paper proposes an innovative conceptual architecture that systematically integrates three core capabilities: shared situational awareness, coordinated response, and joint contingency preparedness within a unified collaborative framework. Through conceptual modeling and architectural design, the approach standardizes information exchange channels, interoperability protocols, and collaborative workflows. Aligned with European Union regulatory requirements, the proposed architecture offers a practical blueprint for national and transnational cybersecurity cooperation, significantly enhancing national cyber resilience, cross-border coordination efficiency, and oversight of critical infrastructure.
0 citationsRead paper
VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
This work addresses the challenge of incomplete 3D scene geometry in single RGB images caused by occlusions by proposing a generative reconstruction framework. Departing from conventional per-pixel or point-cloud querying strategies, the method employs a structured voxel representation to enable efficient surface extraction and large-scale occupancy prediction. It leverages a hybrid 3D variational autoencoder to compress sparse geometry and integrates a latent diffusion Transformer for denoising, augmented with a geometric foundation model that supplies spatial priors. Notably, this is the first application of flow matching to single-view, amodal 3D reconstruction. Evaluated on the ScanNet and NYUv2 datasets, the approach substantially outperforms existing methods, yielding more complete, accurate, and structurally coherent scene reconstructions.
0 citationsRead paper
DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation
This work addresses the challenge of efficiently recovering high-resolution, view-consistent geometry and camera poses from uncalibrated multi-view images or video. We propose a dual-stream Transformer architecture that decouples global consistency modeling from fine-detail preservation: a low-resolution stream alternates between frame-wise and global attention to efficiently estimate camera poses and construct a globally consistent representation, while a high-resolution stream processes raw frames individually to retain fine geometric structures. The two streams are fused via lightweight cross-attention adapters. This design enables independent scaling of resolution and sequence length, supporting inputs up to 2K resolution with low inference cost while effectively integrating global context and local detail. Our method achieves state-of-the-art results on video-based geometry estimation and multi-view reconstruction, producing sharp depth maps and point clouds, strong cross-view consistency, and highly accurate camera poses.
0 citationsRead paper
Adversarial Evasion Attacks on Computer Vision using SHAP Values
This study addresses the vulnerability of computer vision models to adversarial evasion attacks by proposing a novel white-box attack method grounded in SHAP (Shapley Additive Explanations) values. The approach leverages SHAP during inference to quantify the contribution of individual input features to the model’s output, enabling the generation of highly imperceptible adversarial examples. As the first work to integrate SHAP values into adversarial attack strategies, the proposed method demonstrates robust performance even in scenarios where gradient information is limited or obscured. Experimental results show that, compared to the classical Fast Gradient Sign Method (FGSM), this technique achieves superior effectiveness and stability in inducing misclassification while maintaining high attack stealth.
0 citationsRead paper
Recent publications
Latest Papers
BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives
BLARM通过混合潜在刚性运动基元，从单目视频中生成3D物体动画，解决了高维顶点运动预测问题。
0 citationsRead paper
A Blueprint for Collaborative Cybersecurity Operations Centres with Capacity for Shared Situational Awareness, Coordinated Response, and Joint Preparedness
This study addresses the current lack of interoperable cybersecurity operations center architectures capable of supporting cross-border collaboration, shared situational awareness, and joint response—capabilities essential for critical service providers and national entities during large-scale cyber incidents. To bridge this gap, the paper proposes an innovative conceptual architecture that systematically integrates three core capabilities: shared situational awareness, coordinated response, and joint contingency preparedness within a unified collaborative framework. Through conceptual modeling and architectural design, the approach standardizes information exchange channels, interoperability protocols, and collaborative workflows. Aligned with European Union regulatory requirements, the proposed architecture offers a practical blueprint for national and transnational cybersecurity cooperation, significantly enhancing national cyber resilience, cross-border coordination efficiency, and oversight of critical infrastructure.
0 citationsRead paper
VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
This work addresses the challenge of incomplete 3D scene geometry in single RGB images caused by occlusions by proposing a generative reconstruction framework. Departing from conventional per-pixel or point-cloud querying strategies, the method employs a structured voxel representation to enable efficient surface extraction and large-scale occupancy prediction. It leverages a hybrid 3D variational autoencoder to compress sparse geometry and integrates a latent diffusion Transformer for denoising, augmented with a geometric foundation model that supplies spatial priors. Notably, this is the first application of flow matching to single-view, amodal 3D reconstruction. Evaluated on the ScanNet and NYUv2 datasets, the approach substantially outperforms existing methods, yielding more complete, accurate, and structurally coherent scene reconstructions.
0 citationsRead paper
DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation
This work addresses the challenge of efficiently recovering high-resolution, view-consistent geometry and camera poses from uncalibrated multi-view images or video. We propose a dual-stream Transformer architecture that decouples global consistency modeling from fine-detail preservation: a low-resolution stream alternates between frame-wise and global attention to efficiently estimate camera poses and construct a globally consistent representation, while a high-resolution stream processes raw frames individually to retain fine geometric structures. The two streams are fused via lightweight cross-attention adapters. This design enables independent scaling of resolution and sequence length, supporting inputs up to 2K resolution with low inference cost while effectively integrating global context and local detail. Our method achieves state-of-the-art results on video-based geometry estimation and multi-view reconstruction, producing sharp depth maps and point clouds, strong cross-view consistency, and highly accurate camera poses.
0 citationsRead paper
Adversarial Evasion Attacks on Computer Vision using SHAP Values
This study addresses the vulnerability of computer vision models to adversarial evasion attacks by proposing a novel white-box attack method grounded in SHAP (Shapley Additive Explanations) values. The approach leverages SHAP during inference to quantify the contribution of individual input features to the model’s output, enabling the generation of highly imperceptible adversarial examples. As the first work to integrate SHAP values into adversarial attack strategies, the proposed method demonstrates robust performance even in scenarios where gradient information is limited or obscured. Experimental results show that, compared to the classical Fast Gradient Sign Method (FGSM), this technique achieves superior effectiveness and stability in inducing misclassification while maintaining high attack stealth.
0 citationsRead paper