# Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion

arXiv: https://arxiv.org/abs/2012.10296 · HTML: https://mlsanity.com/paper/2012.10296/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2020.

## Built on by (most cited first, 14 of 14)

- [Tri-Perspective View Decomposition for Geometry-Aware Depth Completion](https://mlsanity.com/paper/2403.15008/) (2024)
- [Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting](https://mlsanity.com/paper/2404.19758/) (2024)
- [RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2309.00655/) (2023)
- [GET-UP: GEomeTric-aware Depth Estimation with Radar Points UPsampling](https://mlsanity.com/paper/2409.02720/) (2024)
- [Towards Domain-agnostic Depth Completion](https://mlsanity.com/paper/2207.14466/) (2022)
- [LiRCDepth: Lightweight Radar-Camera Depth Estimation via Knowledge Distillation and Uncertainty Guidance](https://mlsanity.com/paper/2412.16380/) (2024)
- [Beyond Visual Field of View: Perceiving 3D Environment with Echoes and Vision](https://mlsanity.com/paper/2207.01136/) (2022)
- [DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions](https://mlsanity.com/paper/2403.12202/) (2024)
- [Revisiting PatchMatch Multi-View Stereo for Urban 3D Reconstruction](https://mlsanity.com/paper/2207.08439/) (2022)
- [Sparse SPN: Depth Completion from Sparse Keypoints](https://mlsanity.com/paper/2212.00987/) (2022)
- [Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss](https://mlsanity.com/paper/2108.11098/) (2021)
- [Hybrid Transformer Based Feature Fusion for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2211.11066/) (2022)
- [Deep Cost Ray Fusion for Sparse Depth Video Completion](https://mlsanity.com/paper/2409.14935/) (2024)
- [ToFormer: Towards Large-scale Scenario Depth Completion for Lightweight ToF Camera](https://mlsanity.com/paper/2603.20669/) (2026)

## Abstract (arXiv)

In this paper, we propose enhancing monocular depth estimation by adding 3D points as depth guidance. Unlike existing depth completion methods, our approach performs well on extremely sparse and unevenly distributed point clouds, which makes it agnostic to the source of the 3D points. We achieve this by introducing a novel multi-scale 3D point fusion network that is both lightweight and efficient. We demonstrate its versatility on two different depth estimation problems where the 3D points have been acquired with conventional structure-from-motion and LiDAR. In both cases, our network performs on par with state-of-the-art depth completion methods and achieves significantly higher accuracy when only a small number of points is used while being more compact in terms of the number of parameters. We show that our method outperforms some contemporary deep learning based multi-view stereo and structure-from-motion methods both in accuracy and in compactness.