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

• URL: http://arxiv.org/abs/2603.06860v1
• Date: Fri, 06 Mar 2026 20:25:42 GMT
• Title: ColonSplat: Reconstruction of Peristaltic Motion in Colonoscopy with Dynamic Gaussian Splatting
• Abstract summary: ColonSplat is a dynamic Gaussian Splatting framework that captures peristaltic-like motion while preserving global geometric consistency.<n>It achieves superior geometric fidelity on C3VDv2 and DynamicColon datasets.
• Score: 2.0985839017885257
• License: http://creativecommons.org/licenses/by/4.0/
• 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

Related papers

• GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis [94.20462261657525]
  GrainGS is a dynamic framework that combines a hierarchical anchor scaffold with per-Gaussian deformation.<n>It achieves high reconstruction quality, real-time novel view synthesis, and compact storage.
  arXiv  Detail & Related papers  (2026-07-23T15:52:35Z)
• C3VD-DEFCOL: A Deformable Colonoscopy Dataset with Time-Resolved 3D Ground Truth and Realistic Appearance [2.1290430772503415]
  We present C3VD-DEFCOL, a framework and dataset for evaluating deformable colonoscopy reconstruction with paired geometry and realistic texture.<n>C3VD-DEFCOL is designed as a reproducible, quantitative evaluation platform for testing deformable 3D reconstruction algorithms.
  arXiv  Detail & Related papers  (2026-06-05T22:59:32Z)
• CoGE: Sim-to-Real Online Geometric Estimation for Monocular Colonoscopy [6.215033656830097]
  CoGE is a novel framework for online monocular geometric estimation during colonoscopy.<n>An illumination-aware supervision module is proposed to address illumination diversity in different colonoscopy scenes.<n>A structure-aware perception module is proposed to extract common structural and local features of the colon.
  arXiv  Detail & Related papers  (2026-05-13T05:46:39Z)
• MotionScale: Reconstructing Appearance, Geometry, and Motion of Dynamic Scenes with Scalable 4D Gaussian Splatting [54.859943475818234]
  MotionScale is a 4D Gaussian Splatting framework that scales efficiently to large scenes and extended sequences.<n>Experiments on challenging real-world benchmarks demonstrate that MotionScale significantly outperforms state-of-the-art methods in both reconstruction quality and temporal stability.
  arXiv  Detail & Related papers  (2026-03-31T06:03:59Z)
• RealSynCol: a high-fidelity synthetic colon dataset for 3D reconstruction applications [33.26682919703966]
  We propose RealSynCol, a highly realistic synthetic dataset designed to replicate the endoscopic environment.<n>The resulting dataset comprises 28,130 frames, paired with ground truth depth maps, optical flow, 3D meshes, and camera trajectories.<n>Results demonstrate that the high realism and variability of RealSynCol significantly enhance generalization performance on clinical images.
  arXiv  Detail & Related papers  (2026-02-09T08:57:37Z)
• ColonCrafter: A Depth Estimation Model for Colonoscopy Videos Using Diffusion Priors [1.9437590375121516]
  ColonCrafter is a diffusion-based depth estimation model that generates temporally consistent depth maps from monocular colonoscopy videos.<n>Our approach learns robust geometric priors from synthetic colonoscopy sequences to generate temporally consistent depth maps.
  arXiv  Detail & Related papers  (2025-09-16T20:40:22Z)
• X$^{2}$-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction [64.2059940799033]
  Current methods discretize temporal resolution into fixed phases with respiratory gating devices.<n>X$2$-Gaussian, a novel framework, enables continuous-time 4DCT reconstruction by integrating dynamic radiative splatting with self-supervised respiratory motion learning.
  arXiv  Detail & Related papers  (2025-03-27T17:59:57Z)
• DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes [71.61083731844282]
  We present DeSiRe-GS, a self-supervised gaussian splatting representation.<n>It enables effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios.
  arXiv  Detail & Related papers  (2024-11-18T05:49:16Z)
• SMORE: Simultaneous Map and Object REconstruction [66.66729715211642]
  We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR.<n>We take a holistic perspective and optimize a compositional model of a dynamic scene that decomposes the world into rigidly-moving objects and the background.
  arXiv  Detail & Related papers  (2024-06-19T23:53:31Z)
• GaussianBody: Clothed Human Reconstruction via 3d Gaussian Splatting [14.937297984020821]
  We propose a novel clothed human reconstruction method called GaussianBody, based on 3D Gaussian Splatting. Applying the static 3D Gaussian Splatting model to the dynamic human reconstruction problem is non-trivial due to complicated non-rigid deformations and rich cloth details. We show that our method can achieve state-of-the-art photorealistic novel-view rendering results with high-quality details for dynamic clothed human bodies.
  arXiv  Detail & Related papers  (2024-01-18T04:48:13Z)
• ColonNeRF: High-Fidelity Neural Reconstruction of Long Colonoscopy [20.617076071039282]
  ColonNeRF is a novel reconstruction framework based on neural rendering for novel view synthesis of long-sequence colonoscopy. ColonNeRF reduces shape dissimilarity and ensures geometric consistency in each segment. Our reconstruction visualizations show much clearer textures and more accurate geometric details.
  arXiv  Detail & Related papers  (2023-12-04T16:38:16Z)
• CryoFormer: Continuous Heterogeneous Cryo-EM Reconstruction using Transformer-based Neural Representations [49.49939711956354]
  Cryo-electron microscopy (cryo-EM) allows for the high-resolution reconstruction of 3D structures of proteins and other biomolecules. It is still challenging to reconstruct the continuous motions of 3D structures from noisy and randomly oriented 2D cryo-EM images. We propose CryoFormer, a new approach for continuous heterogeneous cryo-EM reconstruction.
  arXiv  Detail & Related papers  (2023-03-28T18:59:17Z)
• C$^3$Fusion: Consistent Contrastive Colon Fusion, Towards Deep SLAM in Colonoscopy [0.0]
  3D colon reconstruction from Optical Colonoscopy (OC) to detect non-examined surfaces remains an unsolved problem. Recent methods demonstrate compelling results, but suffer from: (1) frangible frame-to-frame (or frame-to-model) pose estimation resulting in many tracking failures; or (2) rely on point-based representations at the cost of scan quality. We propose a novel reconstruction framework that addresses these issues end to end, which result in both quantitatively and qualitatively accurate and robust 3D colon reconstruction.
  arXiv  Detail & Related papers  (2022-06-04T10:38:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.