# Deep Depth Completion of a Single RGB-D Image

arXiv: https://arxiv.org/abs/1803.09326 · HTML: https://mlsanity.com/paper/1803.09326/

## Key facts

- Cited by 110 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2018.

## Built on by (most cited first, 30 of 110)

- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [Stereo Correspondence and Reconstruction of Endoscopic Data Challenge](https://mlsanity.com/paper/2101.01133/) (2021)
- [CompletionFormer: Depth Completion with Convolutions and Vision Transformers](https://mlsanity.com/paper/2304.13030/) (2023)
- [RigNet: Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2107.13802/) (2021)
- [Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs](https://mlsanity.com/paper/2304.10532/) (2023)
- [Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors](https://mlsanity.com/paper/2503.17316/) (2025)
- [RGB-D Local Implicit Function for Depth Completion of Transparent Objects](https://mlsanity.com/paper/2104.00622/) (2021)
- [Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline](https://mlsanity.com/paper/2104.06174/) (2021)
- [Unsupervised Depth Completion with Calibrated Backprojection Layers](https://mlsanity.com/paper/2108.10531/) (2021)
- [Bilateral Propagation Network for Depth Completion](https://mlsanity.com/paper/2403.11270/) (2024)
- [InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior](https://mlsanity.com/paper/2404.11613/) (2024)
- [TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline](https://mlsanity.com/paper/2202.08471/) (2022)
- [Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion](https://mlsanity.com/paper/2412.13389/) (2024)
- [ClearPose: Large-scale Transparent Object Dataset and Benchmark](https://mlsanity.com/paper/2203.03890/) (2022)
- [GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer](https://mlsanity.com/paper/2406.01210/) (2024)
- [Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image](https://mlsanity.com/paper/2208.13241/) (2022)
- [Learning Topology from Synthetic Data for Unsupervised Depth Completion](https://mlsanity.com/paper/2106.02994/) (2021)
- [Deep Depth Completion from Extremely Sparse Data: A Survey](https://mlsanity.com/paper/2205.05335/) (2022)
- [An Adaptive Framework for Learning Unsupervised Depth Completion](https://mlsanity.com/paper/2106.03010/) (2021)
- [BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learning](https://mlsanity.com/paper/2112.06179/) (2021)
- [DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Image](https://mlsanity.com/paper/2209.13362/) (2022)
- [Test-Time Adaptation for Depth Completion](https://mlsanity.com/paper/2402.03312/) (2024)
- [Beyond Image to Depth: Improving Depth Prediction using Echoes](https://mlsanity.com/paper/2103.08468/) (2021)
- [Optimal Transport for Unsupervised Denoising Learning](https://mlsanity.com/paper/2108.02574/) (2021)
- [Monitored Distillation for Positive Congruent Depth Completion](https://mlsanity.com/paper/2203.16034/) (2022)
- [OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations](https://mlsanity.com/paper/2406.11711/) (2024)
- [Bayesian Deep Basis Fitting for Depth Completion with Uncertainty](https://mlsanity.com/paper/2103.15254/) (2021)
- [A Surface Geometry Model for LiDAR Depth Completion](https://mlsanity.com/paper/2104.08466/) (2021)
- [CodeMapping: Real-Time Dense Mapping for Sparse SLAM using Compact Scene Representations](https://mlsanity.com/paper/2107.08994/) (2021)
- [AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation](https://mlsanity.com/paper/2310.09739/) (2023)

## Abstract (arXiv)

The goal of our work is to complete the depth channel of an RGB-D image. Commodity-grade depth cameras often fail to sense depth for shiny, bright, transparent, and distant surfaces. To address this problem, we train a deep network that takes an RGB image as input and predicts dense surface normals and occlusion boundaries. Those predictions are then combined with raw depth observations provided by the RGB-D camera to solve for depths for all pixels, including those missing in the original observation. This method was chosen over others (e.g., inpainting depths directly) as the result of extensive experiments with a new depth completion benchmark dataset, where holes are filled in training data through the rendering of surface reconstructions created from multiview RGB-D scans. Experiments with different network inputs, depth representations, loss functions, optimization methods, inpainting methods, and deep depth estimation networks show that our proposed approach provides better depth completions than these alternatives.