Presents the GastroNVS dataset of real gastroscopic images with poses and point cloud, evaluates 3DGS methods on it, and discusses challenges.
Endogaussian: Real-time gaussian splat- ting for dynamic endoscopic scene reconstruction
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
EndoVGGT uses a dynamic DeGAT graph attention module to improve depth estimation and non-rigid 3D reconstruction in surgery, reporting 24.6% PSNR and 9.1% SSIM gains on SCARED with zero-shot generalization to new domains.
G-SHARP is a Gaussian splatting pipeline for real-time deformable tissue reconstruction in surgery, built on the open GSplat rasterizer and deployed via Holoscan on NVIDIA edge hardware with claimed state-of-the-art results on the EndoNeRF benchmark.
A survey compiling principles, applications, benchmarks, and challenges of 3D Gaussian Splatting for explicit 3D scene representation.
citing papers explorer
-
Gastroendoscopy View Synthesis: A New Real Dataset and Evaluation
Presents the GastroNVS dataset of real gastroscopic images with poses and point cloud, evaluates 3DGS methods on it, and discusses challenges.
-
EndoVGGT: GNN-Enhanced Depth Estimation for Surgical 3D Reconstruction
EndoVGGT uses a dynamic DeGAT graph attention module to improve depth estimation and non-rigid 3D reconstruction in surgery, reporting 24.6% PSNR and 9.1% SSIM gains on SCARED with zero-shot generalization to new domains.
-
G-SHARP: Gaussian Surgical Hardware Accelerated Real-time Pipeline
G-SHARP is a Gaussian splatting pipeline for real-time deformable tissue reconstruction in surgery, built on the open GSplat rasterizer and deployed via Holoscan on NVIDIA edge hardware with claimed state-of-the-art results on the EndoNeRF benchmark.
-
A Survey on 3D Gaussian Splatting
A survey compiling principles, applications, benchmarks, and challenges of 3D Gaussian Splatting for explicit 3D scene representation.