Pith. sign in

REVIEW 6 cited by

EndoGaussian: Real-time Gaussian Splatting for Dynamic Endoscopic Scene Reconstruction

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.12561 v2 pith:N4E4EVCV submitted 2024-01-23 cs.CV

Yifan Liu , Chenxin Li , Chen Yang , Yixuan Yuan This is my paper · ORCID
classification cs.CV
keywords gaussianrenderingendoscopicreal-timedeformationendogaussianinitializationscene
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Reconstructing deformable tissues from endoscopic videos is essential in many downstream surgical applications. However, existing methods suffer from slow rendering speed, greatly limiting their practical use. In this paper, we introduce EndoGaussian, a real-time endoscopic scene reconstruction framework built on 3D Gaussian Splatting (3DGS). By integrating the efficient Gaussian representation and highly-optimized rendering engine, our framework significantly boosts the rendering speed to a real-time level. To adapt 3DGS for endoscopic scenes, we propose two strategies, Holistic Gaussian Initialization (HGI) and Spatio-temporal Gaussian Tracking (SGT), to handle the non-trivial Gaussian initialization and tissue deformation problems, respectively. In HGI, we leverage recent depth estimation models to predict depth maps of input binocular/monocular image sequences, based on which pixels are re-projected and combined for holistic initialization. In SPT, we propose to model surface dynamics using a deformation field, which is composed of an efficient encoding voxel and a lightweight deformation decoder, allowing for Gaussian tracking with minor training and rendering burden. Experiments on public datasets demonstrate our efficacy against prior SOTAs in many aspects, including better rendering speed (195 FPS real-time, 100$\times$ gain), better rendering quality (37.848 PSNR), and less training overhead (within 2 min/scene), showing significant promise for intraoperative surgery applications. Code is available at: \url{https://yifliu3.github.io/EndoGaussian/}.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Endo-4DGX: Robust Endoscopic Scene Reconstruction and Illumination Correction with Gaussian Splatting

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Endo-4DGX extends 4D Gaussian Splatting with per-view illumination embeddings, local and global brightness adjustments, and an exposure control loss, improving reconstruction and illumination correction of endoscopic ...

  2. Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A two-level 2D Gaussian splatting method with direct covariance optimization fits large images with more Gaussian points and higher PSNR than prior Gaussian-based image representation.

  3. DeGenseGS: Geometrically and Semantically Decoupled Surgical Scene Understanding in 4D Gaussian Splatting

    cs.CV 2026-07 conditional novelty 5.5 of 10

    Decoupling geometry and semantics in 4DGS via HexPlane kinematic latents and rasterization-native extraction raises surgical semantic mIoU from 53.46% to 68.20% on CholecSeg8k.

  4. ROOM: A Physics-Based Continuum Robot Simulator for Photorealistic Medical Datasets Generation

    cs.RO 2025-09 conditional novelty 5.0 of 10

    ROOM is an open simulation pipeline that generates photorealistic, multimodal synthetic bronchoscopy data from CT scans, and fine-tuning depth models on this data improves their performance on an external phantom-base...

  5. SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting

    eess.IV 2025-06 conditional novelty 5.0 of 10

    SurgTPGS is a text-promptable 3D Gaussian Splatting pipeline that segments surgical instruments and anatomy from natural-language queries at interactive frame rates.

  6. ColorGS: High-fidelity Surgical Scene Reconstruction with Colored Gaussian Splatting

    cs.CV 2025-08 conditional novelty 3.0 of 10

    ColorGS adds spatially anchored colors and a time-independent deformation offset to 3D Gaussian Splatting, achieving 39.85 PSNR on EndoNeRF, 1.5 dB above Deform3DGS.

Pith tools