SAGS: Self-Adaptive Alias-Free Gaussian Splatting for Dynamic Surgical Endoscopic Reconstruction

TL;DR

This paper introduces SAGS, a self-adaptive Gaussian splatting framework that effectively reduces artifacts and improves visualization in dynamic endoscopic tissue reconstruction, surpassing existing methods in quality and efficiency.

Contribution

We propose a novel self-adaptive alias-free Gaussian splatting method with an attention-driven deformation decoder for improved deformable tissue reconstruction.

Findings

Outperforms state-of-the-art in PSNR, SSIM, LPIPS metrics

Reduces artifacts and enhances tissue detail capture

Achieves faster and higher-quality reconstructions on benchmarks

Abstract

Surgical reconstruction of dynamic tissues from endoscopic videos is a crucial technology in robot-assisted surgery. The development of Neural Radiance Fields (NeRFs) has greatly advanced deformable tissue reconstruction, achieving high-quality results from video and image sequences. However, reconstructing deformable endoscopic scenes remains challenging due to aliasing and artifacts caused by tissue movement, which can significantly degrade visualization quality. The introduction of 3D Gaussian Splatting (3DGS) has improved reconstruction efficiency by enabling a faster rendering pipeline. Nevertheless, existing 3DGS methods often prioritize rendering speed while neglecting these critical issues. To address these challenges, we propose SAGS, a self-adaptive alias-free Gaussian splatting framework. We introduce an attention-driven, dynamically weighted 4D deformation decoder, leveraging 3D smoothing filters and 2D Mip filters to mitigate artifacts in deformable tissue reconstruction and better capture the fine details of tissue movement. Experimental results on two public benchmarks, EndoNeRF and SCARED, demonstrate that our method achieves superior performance in all metrics of PSNR, SSIM, and LPIPS compared to the state of the art while also delivering better visualization quality.