Diff2DGS: 通过2D高斯点散布实现遮挡手术场景的可靠重建
Diff2DGS: Reliable Reconstruction of Occluded Surgical Scenes via 2D Gaussian Splatting
AI总结：
Diff2DGS通过两阶段框架提升遮挡手术场景的3D重建精度，结合扩散模型和可学习变形模型，实现更准确的几何和外观重建。
摘要：
实时重建可变形手术场景对推进机器人手术、提高外科医生指导和实现自动化至关重要。最近的方法通过达芬奇机器人手术视频实现密集重建，高斯点散布（GS）通过图形加速提供实时性能。然而，遮挡区域的重建质量仍然有限，深度精度尚未完全评估，因为像EndoNeRF和StereoMIS这样的基准缺乏3D真实数据。我们提出Diff2DGS，一种新的两阶段框架，用于可靠地重建遮挡手术场景。第一阶段中，基于扩散的视频模块结合时间先验信息，能够高空间时间一致性地填补由仪器遮挡的组织。第二阶段中，我们采用2D高斯点散布（2DGS）并结合可学习变形模型（LDM）来捕捉动态组织变形和解剖几何。我们还扩展了评估范围，通过在SCARED数据集上进行定量深度精度分析，超越了以往仅基于图像质量的评估指标。Diff2DGS在外观和几何上均优于现有最先进方法，分别在EndoNeRF和StereoMIS上达到38.02 dB PSNR和34.40 dB。此外，我们的实验表明，仅优化图像质量并不一定带来最优的3D重建精度。为此，我们进一步优化重建3D结果的深度质量，确保更忠实的几何结构，同时保持高质量的外观。
英文摘要：
Real-time reconstruction of deformable surgical scenes is vital for advancing robotic surgery, improving intraoperative guidance, and enabling automation. Recent methods achieve dense reconstructions from da Vinci robotic surgery videos, with Gaussian Splatting (GS) offering real-time performance via graphics acceleration. However, reconstruction quality in occluded regions remains limited, and depth accuracy has not been fully assessed, as benchmarks like EndoNeRF and StereoMIS lack 3D ground truth. We propose Diff2DGS, a two-stage framework for reliable 3D reconstruction of occluded surgical scenes. First, a diffusion-based video module with temporal priors inpaints tissue occluded by instruments with high spatiotemporal consistency. Second, we adapt 2D Gaussian Splatting (2DGS) with a Learnable Deformation Model (LDM) to capture dynamic tissue deformation and anatomical geometry, and introduce adaptive depth weight to improve geometric fidelity. We further extend evaluation beyond image-quality metrics by performing quantitative depth analysis on the SCARED dataset. Diff2DGS outperforms state-of-the-art methods in both appearance and geometry, reaching 38.02 dB PSNR on EndoNeRF and 34.40 dB on StereoMIS. Our experiments also show that optimizing image quality alone does not necessarily ensure accurate 3D geometry.The code is available at https://diff2dgs.github.io/.
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。
