# SelfDeco: Self-Supervised Monocular Depth Completion in Challenging Indoor Environments

arXiv: https://arxiv.org/abs/2011.04977 · HTML: https://mlsanity.com/paper/2011.04977/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2020.

## Built on by (most cited first, 13 of 13)

- [FeatUp: A Model-Agnostic Framework for Features at Any Resolution](https://mlsanity.com/paper/2403.10516/) (2024)
- [Learning Depth Estimation for Transparent and Mirror Surfaces](https://mlsanity.com/paper/2307.15052/) (2023)
- [Deep Depth Completion from Extremely Sparse Data: A Survey](https://mlsanity.com/paper/2205.05335/) (2022)
- [Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR](https://mlsanity.com/paper/2109.09628/) (2021)
- [Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities from Visual SLAM](https://mlsanity.com/paper/2204.13877/) (2022)
- [RGB Guided ToF Imaging System: A Survey of Deep Learning-based Methods](https://mlsanity.com/paper/2405.10357/) (2024)
- [DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes](https://mlsanity.com/paper/2108.05615/) (2021)
- [SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning](https://mlsanity.com/paper/2203.05332/) (2022)
- [RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization](https://mlsanity.com/paper/2509.23991/) (2025)
- [Monocular Depth Decomposition of Semi-Transparent Volume Renderings](https://mlsanity.com/paper/2206.13282/) (2022)
- [SHLE: Devices Tracking and Depth Filtering for Stereo-based Height Limit Estimation](https://mlsanity.com/paper/2212.11538/) (2022)
- [SelfReDepth: Self-Supervised Real-Time Depth Restoration for Consumer-Grade Sensors](https://mlsanity.com/paper/2406.03388/) (2024)
- [Training Self-Supervised Depth Completion Using Sparse Measurements and a Single Image](https://mlsanity.com/paper/2507.14845/) (2025)

## Abstract (arXiv)

We present a novel algorithm for self-supervised monocular depth completion. Our approach is based on training a neural network that requires only sparse depth measurements and corresponding monocular video sequences without dense depth labels. Our self-supervised algorithm is designed for challenging indoor environments with textureless regions, glossy and transparent surface, non-Lambertian surfaces, moving people, longer and diverse depth ranges and scenes captured by complex ego-motions. Our novel architecture leverages both deep stacks of sparse convolution blocks to extract sparse depth features and pixel-adaptive convolutions to fuse image and depth features. We compare with existing approaches in NYUv2, KITTI, and NAVERLABS indoor datasets, and observe 5-34 % improvements in root-means-square error (RMSE) reduction.