ColonSplat: Reconstruction of Peristaltic Motion in Colonoscopy with Dynamic Gaussian Splatting

2026-03-06

AI Summary

This study addresses the challenge that existing endoscopic 3D reconstruction methods struggle to accurately model dynamic deformations caused by peristalsis during colonoscopy, leading to insufficient global geometric consistency. To overcome this limitation, the authors propose a dynamic Gaussian splatting–based reconstruction framework that explicitly models colonic peristalsis while preserving the static anatomical essence of the colon, thereby achieving high-fidelity 3D reconstructions. The work introduces the first dynamic reconstruction benchmark tailored to colonoscopy and releases DynamicColon, a synthetic dataset with ground-truth point clouds. Furthermore, it presents a trajectory-agnostic dynamic Gaussian representation capable of effectively capturing realistic peristaltic deformations while ensuring global geometric consistency. Experiments demonstrate that the proposed method significantly outperforms existing approaches on both C3VDv2 and DynamicColon, achieving more accurate motion modeling and higher geometric fidelity.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Accurate 3D reconstruction of colonoscopy data, accounting for complex peristaltic movements, is crucial for advanced surgical navigation and retrospective diagnostics. While recent novel view synthesis and 3D reconstruction methods have demonstrated remarkable success in general endoscopic scenarios, they struggle in the highly constrained environment of the colon. Due to the limited field of view of a camera moving through an actively deforming tubular structure, existing endoscopic methods reconstruct the colon appearance only for initial camera trajectory. However, the underlying anatomy remains largely static; instead of updating Gaussians'spatial coordinates (xyz), these methods encode deformation through either rotation, scale or opacity adjustments. In this paper, we first present a benchmark analysis of state-of-the-art dynamic endoscopic methods for realistic colonoscopic scenes, showing that they fail to model true anatomical motion. To enable rigorous evaluation of global reconstruction quality, we introduce DynamicColon, a synthetic dataset with ground-truth point clouds at every timestep. Building on these insights, we propose ColonSplat, a dynamic Gaussian Splatting framework that captures peristaltic-like motion while preserving global geometric consistency, achieving superior geometric fidelity on C3VDv2 and DynamicColon datasets. Project page: https://wmito.github.io/ColonSplat

Problem

• peristaltic motion
• colonoscopy
• 3D reconstruction
• dynamic deformation
• endoscopic imaging

Innovation

• Dynamic Gaussian Splatting
• Peristaltic Motion Modeling
• Colonoscopy Reconstruction
• Geometric Consistency
• Synthetic Endoscopic Dataset