Deform3DGS: Flexible Deformation for Fast Surgical Scene Reconstruction with Gaussian Splatting
Shuojue Yang, Qian Li, Daiyun Shen, Bingchen Gong, Qi Dou, Yueming Jin

TL;DR
Deform3DGS introduces a fast, real-time surgical scene reconstruction method using Gaussian Splatting and a novel deformation model, significantly improving speed and fidelity for intraoperative use.
Contribution
The paper presents a new flexible deformation modeling scheme integrated with Gaussian Splatting for rapid, high-fidelity surgical scene reconstruction during endoscopic procedures.
Findings
Achieves 338.8 FPS rendering speed.
Reduces training time to 1 minute per scene.
Demonstrates superior reconstruction quality on surgical videos.
Abstract
Tissue deformation poses a key challenge for accurate surgical scene reconstruction. Despite yielding high reconstruction quality, existing methods suffer from slow rendering speeds and long training times, limiting their intraoperative applicability. Motivated by recent progress in 3D Gaussian Splatting, an emerging technology in real-time 3D rendering, this work presents a novel fast reconstruction framework, termed Deform3DGS, for deformable tissues during endoscopic surgery. Specifically, we introduce 3D GS into surgical scenes by integrating a point cloud initialization to improve reconstruction. Furthermore, we propose a novel flexible deformation modeling scheme (FDM) to learn tissue deformation dynamics at the level of individual Gaussians. Our FDM can model the surface deformation with efficient representations, allowing for real-time rendering performance. More importantly,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAnatomy and Medical Technology · Medical Imaging Techniques and Applications
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
