用掩码注意力提升3D高斯点云，让机器人更准识别工厂零件
MATT-GS: Masked Attention-based 3DGS for Robot Perception and Object Detection
- 用U2-Net去背景，只保留目标物体数据
- 引入Sobel注意力机制，增强螺钉、线缆等细节捕捉
- 在工厂场景中显著提升视觉保真度与识别精度
本文提出一种基于掩码注意力的3D高斯点云（3DGS）新方法，用于提升工业与智能工厂环境中的机器人感知与物体检测能力。采用U2-Net进行背景去除，从原始图像中分离目标物体，减少干扰，确保模型仅处理相关数据。同时，在3DGS框架中集成基于Sobel滤波的注意力机制，强化对螺钉、线缆及复杂纹理等关键细节的捕捉，以支持高精度任务。通过L1损失、SSIM和PSNR等定量指标评估，对比真实图像与原始3DGS训练基线，结果表明该方法在视觉保真度与细节保留方面均有显著提升，验证了其在复杂工业场景下增强机器人视觉感知与物体识别能力的有效性。
原文摘要 · Abstract (English)
This paper presents a novel masked attention-based 3D Gaussian Splatting (3DGS) approach to enhance robotic perception and object detection in industrial and smart factory environments. U2-Net is employed for background removal to isolate target objects from raw images, thereby minimizing clutter and ensuring that the model processes only relevant data. Additionally, a Sobel filter-based attention mechanism is integrated into the 3DGS framework to enhance fine details - capturing critical features such as screws, wires, and intricate textures essential for high-precision tasks. We validate our approach using quantitative metrics, including L1 loss, SSIM, PSNR, comparing the performance of the background-removed and attention-incorporated 3DGS model against the ground truth images and the original 3DGS training baseline. The results demonstrate significant improves in visual fidelity and detail preservation, highlighting the effectiveness of our method in enhancing robotic vision for object recognition and manipulation in complex industrial settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。