# EndoVGGT: GNN-Enhanced Depth Estimation for Surgical 3D Reconstruction

arXiv: https://arxiv.org/abs/2603.24577 · HTML: https://mlsanity.com/paper/2603.24577/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [Vision GNN: An Image is Worth Graph of Nodes](https://mlsanity.com/paper/2206.00272/) (2022)
- [Neural Rendering for Stereo 3D Reconstruction of Deformable Tissues in Robotic Surgery](https://mlsanity.com/paper/2206.15255/) (2022)
- [Stereo Correspondence and Reconstruction of Endoscopic Data Challenge](https://mlsanity.com/paper/2101.01133/) (2021)
- [EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos](https://mlsanity.com/paper/2307.11307/) (2023)
- [Video-based surgical skill assessment using 3D convolutional neural networks](https://mlsanity.com/paper/1903.02306/) (2019)
- [Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery](https://mlsanity.com/paper/2401.06013/) (2024)
- [EndoGaussian: Real-time Gaussian Splatting for Dynamic Endoscopic Scene Reconstruction](https://mlsanity.com/paper/2401.12561/) (2024)
- [A Review of 3D Reconstruction Techniques for Deformable Tissues in Robotic Surgery](https://mlsanity.com/paper/2408.04426/) (2024)
- [Autonomous Intelligent Navigation for Flexible Endoscopy Using Monocular Depth Guidance and 3-D Shape Planning](https://mlsanity.com/paper/2302.13219/) (2023)
- [EndoLRMGS: Complete Endoscopic Scene Reconstruction combining Large Reconstruction Modelling and Gaussian Splatting](https://mlsanity.com/paper/2503.22437/) (2025)

## Abstract (arXiv)

Accurate 3D reconstruction of deformable soft tissues is essential for surgical robotic perception. However, low-texture surfaces, specular highlights, and instrument occlusions often fragment geometric continuity, posing a challenge for existing fixed-topology approaches. To address this, we propose EndoVGGT, a geometry-centric framework equipped with a Deformation-aware Graph Attention (DeGAT) module. Rather than using static spatial neighborhoods, DeGAT dynamically constructs feature-space semantic graphs to capture long-range correlations among coherent tissue regions. This enables robust propagation of structural cues across occlusions, enforcing global consistency and improving non-rigid deformation recovery. Extensive experiments on SCARED show that our method significantly improves fidelity, increasing PSNR by 24.6% and SSIM by 9.1% over prior state-of-the-art. Crucially, EndoVGGT exhibits strong zero-shot cross-dataset generalization to the unseen SCARED and EndoNeRF domains, confirming that DeGAT learns domain-agnostic geometric priors. These results highlight the efficacy of dynamic feature-space modeling for consistent surgical 3D reconstruction.