# Depth Coefficients for Depth Completion

arXiv: https://arxiv.org/abs/1903.05421 · HTML: https://mlsanity.com/paper/1903.05421/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2019.

## Built on by (most cited first, 30 of 41)

- [RigNet: Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2107.13802/) (2021)
- [PNI : Industrial Anomaly Detection using Position and Neighborhood Information](https://mlsanity.com/paper/2211.12634/) (2022)
- [Bilateral Propagation Network for Depth Completion](https://mlsanity.com/paper/2403.11270/) (2024)
- [Radar-Camera Pixel Depth Association for Depth Completion](https://mlsanity.com/paper/2106.02778/) (2021)
- [Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion](https://mlsanity.com/paper/2412.13389/) (2024)
- [Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image](https://mlsanity.com/paper/2208.13241/) (2022)
- [Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries](https://mlsanity.com/paper/2104.02253/) (2021)
- [Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion](https://mlsanity.com/paper/2103.16690/) (2021)
- [Deep Depth Completion from Extremely Sparse Data: A Survey](https://mlsanity.com/paper/2205.05335/) (2022)
- [Depth Completion using Plane-Residual Representation](https://mlsanity.com/paper/2104.07350/) (2021)
- [GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs](https://mlsanity.com/paper/2210.10758/) (2022)
- [A Surface Geometry Model for LiDAR Depth Completion](https://mlsanity.com/paper/2104.08466/) (2021)
- [RGB-Depth Fusion GAN for Indoor Depth Completion](https://mlsanity.com/paper/2203.10856/) (2022)
- [DenseLiDAR: A Real-Time Pseudo Dense Depth Guided Depth Completion Network](https://mlsanity.com/paper/2108.12655/) (2021)
- [Full-Velocity Radar Returns by Radar-Camera Fusion](https://mlsanity.com/paper/2108.10637/) (2021)
- [Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion](https://mlsanity.com/paper/2312.00844/) (2023)
- [NDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completion](https://mlsanity.com/paper/2311.07166/) (2023)
- [Learning an Efficient Multimodal Depth Completion Model](https://mlsanity.com/paper/2208.10771/) (2022)
- [MIPI 2022 Challenge on RGB+ToF Depth Completion: Dataset and Report](https://mlsanity.com/paper/2209.07057/) (2022)
- [RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion](https://mlsanity.com/paper/2306.03584/) (2023)
- [A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps](https://mlsanity.com/paper/2205.12918/) (2022)
- [Towards Domain-agnostic Depth Completion](https://mlsanity.com/paper/2207.14466/) (2022)
- [SemSegDepth: A Combined Model for Semantic Segmentation and Depth Completion](https://mlsanity.com/paper/2209.00381/) (2022)
- [Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement](https://mlsanity.com/paper/2404.19294/) (2024)
- [Differentiable Diffusion for Dense Depth Estimation from Multi-view Images](https://mlsanity.com/paper/2106.08917/) (2021)
- [MIPI 2023 Challenge on RGB+ToF Depth Completion: Methods and Results](https://mlsanity.com/paper/2304.13916/) (2023)
- [Bridging Spectral-wise and Multi-spectral Depth Estimation via Geometry-guided Contrastive Learning](https://mlsanity.com/paper/2503.00793/) (2025)
- [Depth Completion as Parameter-Efficient Test-Time Adaptation](https://mlsanity.com/paper/2602.14751/) (2026)
- [Depth on Demand: Streaming Dense Depth from a Low Frame Rate Active Sensor](https://mlsanity.com/paper/2409.08277/) (2024)
- [Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss](https://mlsanity.com/paper/2108.11098/) (2021)

## Abstract (arXiv)

Depth completion involves estimating a dense depth image from sparse depth measurements, often guided by a color image. While linear upsampling is straight forward, it results in artifacts including depth pixels being interpolated in empty space across discontinuities between objects. Current methods use deep networks to upsample and "complete" the missing depth pixels. Nevertheless, depth smearing between objects remains a challenge. We propose a new representation for depth called Depth Coefficients (DC) to address this problem. It enables convolutions to more easily avoid inter-object depth mixing. We also show that the standard Mean Squared Error (MSE) loss function can promote depth mixing, and thus propose instead to use cross-entropy loss for DC. With quantitative and qualitative evaluation on benchmarks, we show that switching out sparse depth input and MSE loss with our DC representation and cross-entropy loss is a simple way to improve depth completion performance, and reduce pixel depth mixing, which leads to improved depth-based object detection.