# 3dDepthNet: Point Cloud Guided Depth Completion Network for Sparse Depth and Single Color Image

arXiv: https://arxiv.org/abs/2003.09175 · HTML: https://mlsanity.com/paper/2003.09175/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Mar 2020.

## Built on by (most cited first, 5 of 5)

- [Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries](https://mlsanity.com/paper/2104.02253/) (2021)
- [Depth Completion using Geometry-Aware Embedding](https://mlsanity.com/paper/2203.10912/) (2022)
- [3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling](https://mlsanity.com/paper/2209.09231/) (2022)
- [Deep Cost Ray Fusion for Sparse Depth Video Completion](https://mlsanity.com/paper/2409.14935/) (2024)
- [Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusion](https://mlsanity.com/paper/2603.10584/) (2026)

## Abstract (arXiv)

In this paper, we propose an end-to-end deep learning network named 3dDepthNet, which produces an accurate dense depth image from a single pair of sparse LiDAR depth and color image for robotics and autonomous driving tasks. Based on the dimensional nature of depth images, our network offers a novel 3D-to-2D coarse-to-fine dual densification design that is both accurate and lightweight. Depth densification is first performed in 3D space via point cloud completion, followed by a specially designed encoder-decoder structure that utilizes the projected dense depth from 3D completion and the original RGB-D images to perform 2D image completion. Experiments on the KITTI dataset show our network achieves state-of-art accuracy while being more efficient. Ablation and generalization tests prove that each module in our network has positive influences on the final results, and furthermore, our network is resilient to even sparser depth.