ExtraGS: Enhancing Endoscopic View Extrapolation via Diffusion-Guided 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2607.12785v2
• Date: Wed, 15 Jul 2026 04:45:03 GMT
• Title: ExtraGS: Enhancing Endoscopic View Extrapolation via Diffusion-Guided 3D Gaussian Splatting
• Abstract summary: ExtraGS is a framework for enhancing endoscopic view extrapolation through 3D Gaussian Splatting.<n>We show that ExtraGS significantly reduces extrapolation artifacts and achieves state-of-the-art performance in endoscopic novel view synthesis.
• Score: 35.304387516885875
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Robot-assisted minimally invasive surgery (MIS) critically depends on reliable endoscopic perception for navigation and safety. However, conventional endoscopes provide only a limited field of view, leaving large portions of the surrounding anatomy unobserved. Recent neural rendering approaches, such as Neural Radiance Fields and 3D Gaussian Splatting, enable novel view synthesis from endoscopic videos, but their reliance on sparse observations often leads to severe artifacts when extrapolating beyond the training trajectory. In this work, we propose ExtraGS, a framework for enhancing endoscopic view extrapolation through diffusion-guided 3D Gaussian Splatting. Starting from an initial reconstruction, we introduce an uncertainty-guided virtual camera sampling strategy to actively explore blind spots and maximize information gain. The rendered views from these sampled locations are refined using a diffusion model to recover plausible anatomical structures, producing pseudo-observations that guide further optimization. To prevent the generated content from degrading reliable regions, we adopt a confidence-weighted fine-tuning strategy when incorporating these pseudo-observations. Extensive experiments on multiple public endoscopic datasets demonstrate that ExtraGS significantly reduces extrapolation artifacts and achieves state-of-the-art performance in endoscopic novel view synthesis.

Related papers

• NRGS-SLAM: Monocular Non-Rigid SLAM for Endoscopy via Deformation-Aware 3D Gaussian Splatting [25.805439969022697]
  We propose NRGS-SLAM, a monocular non-rigid SLAM system for endoscopy based on 3D Gaussian Splatting.<n>We show that NRGS-SLAM achieves more accurate camera pose estimation (up to 50% reduction in RMSE) and higher-quality photo-realistic reconstructions than state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-19T09:03:47Z)
• EndoWave: Rational-Wavelet 4D Gaussian Splatting for Endoscopic Reconstruction [18.43808203690038]
  endoscopic scenarios present unique challenges, including photometric inconsistencies, non-rigid tissue motion, and view-dependent highlights.<n>Most 3DGS-based methods rely that solely on appearance constraints for optimizing 3DGS are often insufficient in this context.<n>We present EndoWave, which incorporates an optical flow-based geometric constraint and a multi-resolution rational wavelet supervision.
  arXiv  Detail & Related papers  (2025-10-27T07:45:17Z)
• Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting [95.61137026932062]
  Intern-GS is a novel approach to enhance the process of sparse-view Gaussian splatting.<n>We show that Intern-GS achieves state-of-the-art rendering quality across diverse datasets.
  arXiv  Detail & Related papers  (2025-05-27T05:17:49Z)
• IXGS-Intraoperative 3D Reconstruction from Sparse, Arbitrarily Posed Real X-rays [1.2721397985664153]
  We extend the $R2$-Gaussian splatting framework to reconstruct consistent 3D volumes under challenging conditions.<n>We introduce an anatomy-guided radiographic standardization step using style transfer, improving visual consistency across views.
  arXiv  Detail & Related papers  (2025-04-20T18:28:13Z)
• Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis [53.702118455883095]
  We propose a novel method for synthesizing novel views from sparse views with Gaussian Splatting. Our key idea lies in exploring the self-supervisions inherent in the binocular stereo consistency between each pair of binocular images. Our method significantly outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-24T15:10:27Z)
• EndoSparse: Real-Time Sparse View Synthesis of Endoscopic Scenes using Gaussian Splatting [39.60431471170721]
  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 view synthesis, but they often struggle to recover accurate 3D representations when only sparse observations are available. We propose a framework leveraging the prior knowledge from multiple foundation models during the reconstruction process, dubbed as textitEndoSparse.
  arXiv  Detail & Related papers  (2024-07-01T07:24:09Z)
• High-fidelity Endoscopic Image Synthesis by Utilizing Depth-guided Neural Surfaces [18.948630080040576]
  We introduce a novel method for colon section reconstruction by leveraging NeuS applied to endoscopic images, supplemented by a single frame of depth map. Our approach demonstrates exceptional accuracy in completely rendering colon sections, even capturing unseen portions of the surface. This breakthrough opens avenues for achieving stable and consistently scaled reconstructions, promising enhanced quality in cancer screening procedures and treatment interventions.
  arXiv  Detail & Related papers  (2024-04-20T18:06:26Z)
• DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery [71.6345505427213]
  DPMesh is an innovative framework for occluded human mesh recovery. It capitalizes on the profound diffusion prior about object structure and spatial relationships embedded in a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-04-01T18:59:13Z)
• FLex: Joint Pose and Dynamic Radiance Fields Optimization for Stereo Endoscopic Videos [79.50191812646125]
  Reconstruction of endoscopic scenes is an important asset for various medical applications, from post-surgery analysis to educational training. We adress the challenging setup of a moving endoscope within a highly dynamic environment of deforming tissue. We propose an implicit scene separation into multiple overlapping 4D neural radiance fields (NeRFs) and a progressive optimization scheme jointly optimizing for reconstruction and camera poses from scratch. This improves the ease-of-use and allows to scale reconstruction capabilities in time to process surgical videos of 5,000 frames and more; an improvement of more than ten times compared to the state of the art while being agnostic to external tracking information
  arXiv  Detail & Related papers  (2024-03-18T19:13:02Z)
• AiAReSeg: Catheter Detection and Segmentation in Interventional Ultrasound using Transformers [75.20925220246689]
  endovascular surgeries are performed using the golden standard of Fluoroscopy, which uses ionising radiation to visualise catheters and vasculature. This work proposes a solution using an adaptation of a state-of-the-art machine learning transformer architecture to detect and segment catheters in axial interventional Ultrasound image sequences.
  arXiv  Detail & Related papers  (2023-09-25T19:34:12Z)
• Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction [60.52716381465063]
  We introduce Deceptive-NeRF/3DGS to enhance sparse-view reconstruction with only a limited set of input images. Specifically, we propose a deceptive diffusion model turning noisy images rendered from few-view reconstructions into high-quality pseudo-observations. Our system progressively incorporates diffusion-generated pseudo-observations into the training image sets, ultimately densifying the sparse input observations by 5 to 10 times.
  arXiv  Detail & Related papers  (2023-05-24T14:00:32Z)

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.