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

• URL: http://arxiv.org/abs/2603.24577v1
• Date: Wed, 25 Mar 2026 17:53:34 GMT
• Title: EndoVGGT: GNN-Enhanced Depth Estimation for Surgical 3D Reconstruction
• Abstract summary: EndoVGGT is a geometry-centric framework equipped with a Deformation-aware Graph Attention module.<n>Our method significantly improves fidelity, increasing PSNR by 24.6% and SSIM by 9.1% over prior state-of-the-art.<n>These results highlight the efficacy of dynamic feature-space modeling for consistent surgical 3D reconstruction.
• Score: 4.035026965933258
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• OAHuman: Occlusion-Aware 3D Human Reconstruction from Monocular Images [49.90475154034411]
  OAHuman is a framework that explicitly decouples geometry reconstruction and texture synthesis for robust 3D human modeling from a single RGB image.<n>Our framework ensures geometry reconstruction is perceptually reinforced even in occluded areas, isolating it from texture interference.<n>In parallel, texture synthesis is learned exclusively from visible regions, preventing texture errors from being transferred to the occluded areas.
  arXiv  Detail & Related papers  (2026-03-15T06:57:26Z)
• 3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification [80.43401018217367]
  3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and 3D scene reconstruction.<n>Its quality often degrades in real-world environments due to transient distractors, such as moving objects and varying shadows.<n>Existing methods rely on semantic cues extracted from pre-trained vision models to identify and suppress these distractors.<n>We propose 3DGS- HPC, a framework that circumvents these limitations by combining two complementary principles.
  arXiv  Detail & Related papers  (2026-03-08T11:16:30Z)
• Monocular Endoscopic Tissue 3D Reconstruction with Multi-Level Geometry Regularization [3.696132675621222]
  We introduce a novel approach based on 3D Gaussian Splatting to reconstruct soft endoscopic tissues.<n>Our proposed method delivers a fast rendering process and smooth surface appearances.
  arXiv  Detail & Related papers  (2026-02-24T09:29:36Z)
• Diff2DGS: Reliable Reconstruction of Occluded Surgical Scenes via 2D Gaussian Splatting [10.70948053935438]
  We propose Diff2DGS, a novel two-stage framework for reliable 3D reconstruction of occluded surgical scenes.<n>In the first stage, a diffusion-based video module with temporal priors inpaints tissue occluded by instruments with high spatial-temporal consistency.<n>In the second stage, we adapt 2D Gaussian Splatting (2DGS) with a Learnable Deformation Model (LDM) to capture dynamic tissue deformation and anatomical geometry.<n>D Diff2DGS outperforms state-of-the-art approaches in both appearance and geometry, reaching 38.02 dB PSNR on
  arXiv  Detail & Related papers  (2026-02-20T16:14:21Z)
• TG-Field: Geometry-Aware Radiative Gaussian Fields for Tomographic Reconstruction [16.246538335191982]
  Tomographic Geometry Field (TG-Field) is a geometry-aware Gaussian deformation framework for computed tomography (CT) reconstruction.<n> TG-Field consistently outperforms existing methods, achieving state-of-the-art reconstruction accuracy under highly sparse-view conditions.
  arXiv  Detail & Related papers  (2026-02-12T08:33:01Z)
• ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting [63.138778159026934]
  We propose an adaptive optimization framework guided by excess risk decomposition, termed ERGO.<n> ERGO dynamically estimates the view-specific excess risk and adaptively adjust loss weights during optimization.<n>Experiments on the Google Scanned Objects dataset and the OmniObject3D dataset demonstrate the superiority of ERGO over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-10T20:44:43Z)
• EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopy [41.838228673736076]
  We present EMGauss, a general framework for 3D reconstruction from planar scanned 2D slices with applications in Volume electron microscopy.<n>Our key innovation is to reframe slice-to-3D reconstruction as a 3D dynamic scene rendering problem based on Gaussian splatting.<n>Compared with diffusion- and GAN-based reconstruction methods, EMGauss substantially improves quality, enables continuous slice synthesis, and eliminates the need for large-scale pretraining.
  arXiv  Detail & Related papers  (2025-12-07T06:39:57Z)
• Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification [59.17489431187807]
  We propose a framework that enhances 3D geometric fidelity by leveraging CLIP's hierarchical spatial semantics.<n>Our method significantly improves 3D few-shot class-incremental learning, achieving superior geometric coherence and robustness to texture bias.
  arXiv  Detail & Related papers  (2025-09-18T13:45:08Z)
• Decompositional Neural Scene Reconstruction with Generative Diffusion Prior [64.71091831762214]
  Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture, is intriguing for downstream applications.<n>Recent approaches incorporate semantic or geometric regularization to address this issue, but they suffer significant degradation in underconstrained areas.<n>We propose DP-Recon, which employs diffusion priors in the form of Score Distillation Sampling (SDS) to optimize the neural representation of each individual object under novel views.
  arXiv  Detail & Related papers  (2025-03-19T02:11:31Z)
• Feature-EndoGaussian: Feature Distilled Gaussian Splatting in Surgical Deformable Scene Reconstruction [26.358467072736524]
  We introduce Feature-EndoGaussian (FEG), an extension of 3DGS that integrates 2D segmentation cues into 3D rendering to enable real-time semantic and scene reconstruction.<n>FEG achieves superior performance (SSIM of 0.97, PSNR of 39.08, and LPIPS of 0.03) compared to leading methods.
  arXiv  Detail & Related papers  (2025-03-08T10:50:19Z)
• Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning [68.9515120904028]
  Limited-angle tomography of strongly scattering quasi-transparent objects is a challenging, highly ill-posed problem. Regularizing priors are necessary to reduce artifacts by improving the condition of such problems. We devised a recurrent neural network (RNN) architecture with a novel split-convolutional gated recurrent unit (SC-GRU) as the building block.
  arXiv  Detail & Related papers  (2020-07-21T11:48:22Z)

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.