EndoLRMGS：结合大型重建建模与高斯溅射的完整内窥镜场景重建
EndoLRMGS: Complete Endoscopic Scene Reconstruction combining Large Reconstruction Modelling and Gaussian Splatting
AI总结：
提出EndoLRMGS，结合大型重建建模与高斯溅射，实现完整手术场景重建，显著提升工具3D模型IoU及渲染质量。
摘要：
手术场景的完整重建对于机器人辅助手术（RAS）至关重要。深度估计方法前景广阔，但现有工作在深度不连续处表现不佳，导致物体边界处预测噪声大，且无法实现完整重建，遗漏被遮挡表面。为解决这些问题，我们提出EndoLRMGS，结合大型重建建模（LRM）和高斯溅射（GS），用于完整手术场景重建。GS重建可变形组织，LRM为手术工具生成3D模型，随后通过引入正交视角联合投影优化（OPjPO）优化位置和尺度以提高精度。在来自三个公共数据集的四个手术视频上的实验中，我们的方法将工具3D模型在2D投影中的交并比（IoU）提高了超过40%。此外，EndoLRMGS将工具投影的峰值信噪比（PSNR）从3.82%提升至11.07%。组织渲染质量也得到改善，在所有测试视频中，PSNR从0.46%提升至49.87%，结构相似性指数（SSIM）从1.53%提升至29.21%。
英文摘要：
Complete reconstruction of surgical scenes is crucial for robot-assisted surgery (RAS). Deep depth estimation is promising but existing works struggle with depth discontinuities, resulting in noisy predictions at object boundaries and do not achieve complete reconstruction omitting occluded surfaces. To address these issues we propose EndoLRMGS, that combines Large Reconstruction Modelling (LRM) and Gaussian Splatting (GS), for complete surgical scene reconstruction. GS reconstructs deformable tissues and LRM generates 3D models for surgical tools while position and scale are subsequently optimized by introducing orthogonal perspective joint projection optimization (OPjPO) to enhance accuracy. In experiments on four surgical videos from three public datasets, our method improves the Intersection-over-union (IoU) of tool 3D models in 2D projections by>40%. Additionally, EndoLRMGS improves the PSNR of the tools projection from 3.82% to 11.07%. Tissue rendering quality also improves, with PSNR increasing from 0.46% to 49.87%, and SSIM from 1.53% to 29.21% across all test videos.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
