Endo-G$^{2}$T: Geometry-Guided & Temporally Aware Time-Embedded 4DGS For Endoscopic Scenes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908677078777856 |
|---|---|
| author | Liu, Yangle Li, Fengze Liu, Kan Ma, Jieming |
| author_facet | Liu, Yangle Li, Fengze Liu, Kan Ma, Jieming |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_21367 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Endo-G$^{2}$T: Geometry-Guided & Temporally Aware Time-Embedded 4DGS For Endoscopic Scenes Liu, Yangle Li, Fengze Liu, Kan Ma, Jieming Computer Vision and Pattern Recognition 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. |
| title | Endo-G$^{2}$T: Geometry-Guided & Temporally Aware Time-Embedded 4DGS For Endoscopic Scenes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.21367 |