EndoSparse: Real-Time Sparse View Synthesis of Endoscopic Scenes using Gaussian Splatting

TL;DR

EndoSparse introduces a novel framework that leverages foundation models to improve real-time 3D reconstruction and view synthesis of endoscopic scenes from sparse observations, enhancing geometric accuracy and rendering quality.

Contribution

It is the first to integrate foundation model priors into endoscopic 3D reconstruction, significantly improving results under sparse-view conditions.

Findings

Outperforms state-of-the-art methods in geometry and appearance quality.

Achieves robust 3D reconstruction with only three views.

Demonstrates real-time rendering efficiency.

Abstract

3D reconstruction of biological tissues from a collection of endoscopic images is a key to unlock various important downstream surgical applications with 3D capabilities. Existing methods employ various advanced neural rendering techniques for photorealistic view synthesis, but they often struggle to recover accurate 3D representations when only sparse observations are available, which is usually the case in real-world clinical scenarios. To tackle this {sparsity} challenge, we propose a framework leveraging the prior knowledge from multiple foundation models during the reconstruction process, dubbed as \textit{EndoSparse}. Experimental results indicate that our proposed strategy significantly improves the geometric and appearance quality under challenging sparse-view conditions, including using only three views. In rigorous benchmarking experiments against state-of-the-art methods, \textit{EndoSparse} achieves superior results in terms of accurate geometry, realistic appearance, and rendering efficiency, confirming the robustness to sparse-view limitations in endoscopic reconstruction. \textit{EndoSparse} signifies a steady step towards the practical deployment of neural 3D reconstruction in real-world clinical scenarios. Project page: https://endo-sparse.github.io/.