Skip to content
Preprint

MV-dVRK: A Multi-Viewpoint Benchmark for Spatial Surgical Perception

Sep 2026 · 0 citations · 48 references
Computer Science

TL;DR

MV-dVRK is presented, the first ex-vivo surgical dataset to combine multiple exposure-synchronized stereo viewpoints with accurate surface geometry and camera poses, and used to systematically compare zero-shot monocular, stereo, multi-stereo, and multi-view 3D reconstruction methods as the number of viewpoints increases.

Abstract

Large-scale training and refined optimization techniques have greatly improved sparse multi-view 3D reconstruction. Despite their relevance to surgery, such methods have never before been rigorously evaluated on real endoscopic images. Current clinical telerobots deploy a single stereo camera inside the patient, making multi-viewpoint data extremely rare. This paper presents MV-dVRK, the first ex-vivo surgical dataset to combine multiple exposure-synchronized stereo viewpoints with accurate surface geometry and camera poses. The static subset of the benchmark provides dense SfM reference geometry, validated against an industrial 3D scanner, together with ground-truth camera poses and sparse-view test sets. We use MV-dVRK to systematically compare zero-shot monocular, stereo, multi-stereo, and multi-view 3D reconstruction methods as the number of viewpoints increases. With two endoscopes, multi-stereo reconstruction achieves the highest coverage. With a third viewpoint, optimization-based multi-view methods perform best, covering 67% of ground-truth surface points within a 1 mm tolerance and recovering highly accurate relative camera poses. By contrast, feed-forward foundation models cover only 43% of the ground-truth surface in the same setting. MV-dVRK also includes ten dynamic sequences spanning multiple surgical tasks, with increasing kinematic complexity and tissue deformation, providing a basis for future research in multi-viewpoint surgical perception. The project is available at: https://mv-dvrk.is.mpg.de.

View source

Similar papers

Open access Aug 2026

Accurate Surgical Scene Reconstruction from Multi-view FoundationStereo

It is demonstrated that FoundationStereo achieves state-of-the-art zero-shot accuracy, and a sub-millimeter mean error for single-frame depth estimation and an error under 2 mm for fused multi-view reconstructions, significantly outperforming the zero-shot STTR baseline.

Yujia Gong · 0 citations
Sep 2026

Colon3R: Cross-Domain 3D Reconstruction from Monocular Colonoscopic Video

Colon3R is presented, a cross-domain semi-supervised framework built on pretrained VGGT that transfers coupled camera, depth, and pointmap geometry from labeled phantom and simulated data to unlabeled in-vivo colonoscopy without requiring target-domain geometric annotations.

Zhi-Hao Xing, Ying-Yu Wang, Liang Zhao et al. · 0 citations
Preprint Aug 2026

ZipMVS: Multi-View Stereo with Compressed Cost Volumes

Multi-view stereo (MVS) methods typically deliver highly accurate 3D reconstructions from multiple registered RGB images, thanks to the highly informative, geometric constraints between them. However, their substantial memory requirements remain a major obstacle for deployment in domains such as aerospace and autonomou...

Guang-Lin Jin, Hongshan Yu, Javier Civera et al. · 0 citations
Preprint Sep 2026

Revisiting Multi-View Stereo: A Sequence-to-Sequence Formulation

Computing accurate geometry from multi-view images is a fundamental problem in computer vision. Recent feed-forward (FF) models jointly estimate 3D geometry and camera parameters, but they typically suffer from geometry distortion caused by reconstruction ambiguity, even when ground-truth camera parameters are supplied...

Ao-Xiang Fan, Corentin Dumery, Nicolas Talabot et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.