# 3D Consistency Optimization for Self-Supervised Monocular Video Depth Estimation

arXiv: https://arxiv.org/abs/2606.15681 · HTML: https://mlsanity.com/paper/2606.15681/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 14 Jun 2026.

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

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views](https://mlsanity.com/paper/2505.23716/) (2025)
- [Video Depth Anything: Consistent Depth Estimation for Super-Long Videos](https://mlsanity.com/paper/2501.12375/) (2025)
- [Endo-Depth-and-Motion: Reconstruction and Tracking in Endoscopic Videos using Depth Networks and Photometric Constraints](https://mlsanity.com/paper/2103.16525/) (2021)
- [Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue](https://mlsanity.com/paper/2112.08122/) (2021)
- [Neural LerPlane Representations for Fast 4D Reconstruction of Deformable Tissues](https://mlsanity.com/paper/2305.19906/) (2023)
- [Endo-4DGS: Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splatting](https://mlsanity.com/paper/2401.16416/) (2024)
- [EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera](https://mlsanity.com/paper/2405.08672/) (2024)
- [SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting](https://mlsanity.com/paper/2411.17190/) (2024)
- [EndoGSLAM: Real-Time Dense Reconstruction and Tracking in Endoscopic Surgeries using Gaussian Splatting](https://mlsanity.com/paper/2403.15124/) (2024)
- [Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video](https://mlsanity.com/paper/2504.03198/) (2025)
- [SurgicalGS: Dynamic 3D Gaussian Splatting for Accurate Robotic-Assisted Surgical Scene Reconstruction](https://mlsanity.com/paper/2410.09292/) (2024)
- [SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting](https://mlsanity.com/paper/2506.23309/) (2025)
- [Endo-FASt3r: Endoscopic Foundation model Adaptation for Structure from motion](https://mlsanity.com/paper/2503.07204/) (2025)
- [Enhanced Scale-aware Depth Estimation for Monocular Endoscopic Scenes with Geometric Modeling](https://mlsanity.com/paper/2408.07266/) (2024)
- [BridgeSplat: Bidirectionally Coupled CT and Non-Rigid Gaussian Splatting for Deformable Intraoperative Surgical Navigation](https://mlsanity.com/paper/2509.18501/) (2025)

## Abstract (arXiv)

Reliable monocular video depth estimation is crucial for downstream 3D reasoning and embodied AI in endoscopic navigation. However, existing self-supervised approaches typically treat video frames independently or rely on weak temporal regularization. These methods, lacking a holistic perception of the underlying 3D scene, inevitably suffer from geometrically inconsistent predictions and severe cross-frame drift. To address these limitations, we introduce a new paradigm that recasts sequential video depth estimation as an unconstrained multi-view 3D reconstruction problem, enabling full exploitation of the powerful geometric priors embedded in recent 3D foundation models. The core of our approach is a 3D consistency optimization framework driven by three constraints: image-level photometric rendering, explicit world-coordinate geometric alignment, and multi-scale temporal gradient consistency. Such unified optimization elegantly anchors isolated frames to a globally coherent 3D structure. Our method has been validated in both the self-supervised training scenarios and challenging zero-shot clinical environments. Results show that the proposed approach achieves state-of-the-art spatial accuracy, outperforming the frame-based, video-based depth estimators and the multi-view 3D reconstruction baselines.