# Bridging the Ex-Vivo to In-Vivo Gap: Synthetic Priors for Monocular Depth Estimation in Specular Surgical Environments

arXiv: https://arxiv.org/abs/2512.23786 · HTML: https://mlsanity.com/paper/2512.23786/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 29 Dec 2025.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation](https://mlsanity.com/paper/1806.08756/) (2018)
- [Stereo Correspondence and Reconstruction of Endoscopic Data Challenge](https://mlsanity.com/paper/2101.01133/) (2021)
- [Colonoscopy 3D Video Dataset with Paired Depth from 2D-3D Registration](https://mlsanity.com/paper/2206.08903/) (2022)
- [Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue](https://mlsanity.com/paper/2112.08122/) (2021)
- [DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning](https://mlsanity.com/paper/2003.13446/) (2020)
- [Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems](https://mlsanity.com/paper/2106.14386/) (2021)
- [EndoMapper dataset of complete calibrated endoscopy procedures](https://mlsanity.com/paper/2204.14240/) (2022)
- [EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera](https://mlsanity.com/paper/2405.08672/) (2024)
- [DefSLAM: Tracking and Mapping of Deforming Scenes from Monocular Sequences](https://mlsanity.com/paper/1908.08918/) (2019)
- [Multi-View Fusion for Multi-Level Robotic Scene Understanding](https://mlsanity.com/paper/2103.13539/) (2021)
- [ORBSLAM-based Endoscope Tracking and 3D Reconstruction](https://mlsanity.com/paper/1608.08149/) (2016)
- [Deep Causal Learning for Robotic Intelligence](https://mlsanity.com/paper/2212.12597/) (2022)
- [Single-Camera 3D Head Fitting for Mixed Reality Clinical Applications](https://mlsanity.com/paper/2109.02740/) (2021)

## Abstract (arXiv)

Accurate Monocular Depth Estimation (MDE) is critical for autonomous robotic surgery. However, existing self-supervised methods often exhibit a severe "ex-vivo to in-vivo gap": they achieve high accuracy on public datasets but struggle in actual clinical deployments. This disparity arises because the severe specular reflections and fluid-filled deformations inherent to real surgeries. Models trained on noisy real-world pseudo-labels consequently suffer from severe boundary collapse. To address this, we leverage the high-fidelity synthetic priors of the textitDepth Anything V2 architecture, which inherently capture precise geometric details, and efficiently adapt them to the medical domain using Dynamic Vector Low-Rank Adaptation (DV-LORA). Our contributions are two-fold. Technically, our approach establishes a new state-of-the-art on the public SCARED dataset; under a novel physically-stratified evaluation protocol, it reduces Squared Relative Error by over 17% in high-specularity regimes compared to strong baselines. Furthermore, to provide a rigorous reality check for the field, we introduce ROCAL-T 90 (Real Operative CT-Aligned Laparoscopic Trajectories 90), the first real-surgery validation dataset featuring 90 clinical endoscopic sequences with sub-millimeter (< 1mm) ground-truth trajectories. Evaluations on ROCAL-T 90 demonstrate our model's superior robustness in true clinical settings.