# Monocular Depth Estimation with Self-supervised Instance Adaptation

arXiv: https://arxiv.org/abs/2004.05821 · HTML: https://mlsanity.com/paper/2004.05821/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2020.

## Built on by (most cited first, 12 of 12)

- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [SimpleRecon: 3D Reconstruction Without 3D Convolutions](https://mlsanity.com/paper/2208.14743/) (2022)
- [Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2110.08192/) (2021)
- [MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision](https://mlsanity.com/paper/2303.03315/) (2023)
- [CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentation](https://mlsanity.com/paper/2303.10147/) (2023)
- [SfM-TTR: Using Structure from Motion for Test-Time Refinement of Single-View Depth Networks](https://mlsanity.com/paper/2211.13551/) (2022)
- [DoubleTake: Geometry Guided Depth Estimation](https://mlsanity.com/paper/2406.18387/) (2024)
- [DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume](https://mlsanity.com/paper/2308.07225/) (2023)
- [Instance-aware multi-object self-supervision for monocular depth prediction](https://mlsanity.com/paper/2203.00809/) (2022)
- [On the Coupling of Depth and Egomotion Networks for Self-Supervised Structure from Motion](https://mlsanity.com/paper/2106.04007/) (2021)
- [RayTun3R: Online Camera Adaptation in 3D Foundation Models](https://mlsanity.com/paper/2607.02711/) (2026)
- [On depth prediction for autonomous driving using self-supervised learning](https://mlsanity.com/paper/2403.06194/) (2024)

## Abstract (arXiv)

Recent advances in self-supervised learning havedemonstrated that it is possible to learn accurate monoculardepth reconstruction from raw video data, without using any 3Dground truth for supervision. However, in robotics applications,multiple views of a scene may or may not be available, depend-ing on the actions of the robot, switching between monocularand multi-view reconstruction. To address this mixed setting,we proposed a new approach that extends any off-the-shelfself-supervised monocular depth reconstruction system to usemore than one image at test time. Our method builds on astandard prior learned to perform monocular reconstruction,but uses self-supervision at test time to further improve thereconstruction accuracy when multiple images are available.When used to update the correct components of the model, thisapproach is highly-effective. On the standard KITTI bench-mark, our self-supervised method consistently outperformsall the previous methods with an average 25% reduction inabsolute error for the three common setups (monocular, stereoand monocular+stereo), and comes very close in accuracy whencompared to the fully-supervised state-of-the-art methods.