# Plug-and-Play: Improve Depth Estimation via Sparse Data Propagation

arXiv: https://arxiv.org/abs/1812.08350 · HTML: https://mlsanity.com/paper/1812.08350/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2018.

## Built on by (most cited first, 10 of 10)

- [DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Image](https://mlsanity.com/paper/2209.13362/) (2022)
- [Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR](https://mlsanity.com/paper/2109.09628/) (2021)
- [Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback](https://mlsanity.com/paper/2309.15762/) (2023)
- [Advancing Autonomous Driving: DepthSense with Radar and Spatial Attention](https://mlsanity.com/paper/2109.05265/) (2021)
- [Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement](https://mlsanity.com/paper/2404.19294/) (2024)
- [Representation Based Regression for Object Distance Estimation](https://mlsanity.com/paper/2106.14208/) (2021)
- [DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image](https://mlsanity.com/paper/2504.01596/) (2025)
- [DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidance](https://mlsanity.com/paper/2509.26498/) (2025)
- [BIDCD -- Bosch Industrial Depth Completion Dataset](https://mlsanity.com/paper/2108.04706/) (2021)
- [PTA-Det: Point Transformer Associating Point cloud and Image for 3D Object Detection](https://mlsanity.com/paper/2301.07301/) (2023)

## Abstract (arXiv)

We propose a novel plug-and-play (PnP) module for improving depth prediction with taking arbitrary patterns of sparse depths as input. Given any pre-trained depth prediction model, our PnP module updates the intermediate feature map such that the model outputs new depths consistent with the given sparse depths. Our method requires no additional training and can be applied to practical applications such as leveraging both RGB and sparse LiDAR points to robustly estimate dense depth map. Our approach achieves consistent improvements on various state-of-the-art methods on indoor (i.e., NYU-v2) and outdoor (i.e., KITTI) datasets. Various types of LiDARs are also synthesized in our experiments to verify the general applicability of our PnP module in practice. For project page, see https://zswang666.github.io/PnP-Depth-Project-Page/