Endo-G$^{2}$T: Geometry-Guided & Temporally Aware Time-Embedded 4DGS For Endoscopic Scenes
By: Yangle Liu , Fengze Li , Kan Liu and more
Potential Business Impact:
Creates clearer 3D videos from inside the body.
Endoscopic (endo) video exhibits strong view-dependent effects such as specularities, wet reflections, and occlusions. Pure photometric supervision misaligns with geometry and triggers early geometric drift, where erroneous shapes are reinforced during densification and become hard to correct. We ask how to anchor geometry early for 4D Gaussian splatting (4DGS) while maintaining temporal consistency and efficiency in dynamic endoscopic scenes. Thus, we present Endo-G$^{2}$T, a geometry-guided and temporally aware training scheme for time-embedded 4DGS. First, geo-guided prior distillation converts confidence-gated monocular depth into supervision with scale-invariant depth and depth-gradient losses, using a warm-up-to-cap schedule to inject priors softly and avoid early overfitting. Second, a time-embedded Gaussian field represents dynamics in XYZT with a rotor-like rotation parameterization, yielding temporally coherent geometry with lightweight regularization that favors smooth motion and crisp opacity boundaries. Third, keyframe-constrained streaming improves efficiency and long-horizon stability through keyframe-focused optimization under a max-points budget, while non-keyframes advance with lightweight updates. Across EndoNeRF and StereoMIS-P1 datasets, Endo-G$^{2}$T achieves state-of-the-art results among monocular reconstruction baselines.
Similar Papers
TED-4DGS: Temporally Activated and Embedding-based Deformation for 4DGS Compression
CV and Pattern Recognition
Makes moving 3D scenes smaller for faster sharing.
DET-GS: Depth- and Edge-Aware Regularization for High-Fidelity 3D Gaussian Splatting
CV and Pattern Recognition
Makes 3D pictures look real from few photos.
Geometry-Consistent 4D Gaussian Splatting for Sparse-Input Dynamic View Synthesis
CV and Pattern Recognition
Creates realistic 3D scenes from few pictures.