# Relative Depth Estimation as a Ranking Problem

arXiv: https://arxiv.org/abs/2010.06944 · HTML: https://mlsanity.com/paper/2010.06944/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [Single Image Depth Estimation: An Overview](https://mlsanity.com/paper/2104.06456/) (2021)
- [Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency](https://mlsanity.com/paper/2403.17638/) (2024)
- [Depth-Relative Self Attention for Monocular Depth Estimation](https://mlsanity.com/paper/2304.12849/) (2023)
- [RLSEP: Learning Label Ranks for Multi-label Classification](https://mlsanity.com/paper/2212.04022/) (2022)

## Abstract (arXiv)

We present a formulation of the relative depth estimation from a single image problem, as a ranking problem. By reformulating the problem this way, we were able to utilize literature on the ranking problem, and apply the existing knowledge to achieve better results. To this end, we have introduced a listwise ranking loss borrowed from ranking literature, weighted ListMLE, to the relative depth estimation problem. We have also brought a new metric which considers pixel depth ranking accuracy, on which our method is stronger.