# Depth Coefficients for Depth Completion

## TL;DR

This paper introduces Depth Coefficients (DC), a novel depth representation that reduces depth mixing artifacts in depth completion, improving accuracy and object detection by replacing traditional input and loss functions.

## Contribution

The authors propose Depth Coefficients (DC) for depth completion, enabling better separation of objects and replacing MSE with cross-entropy loss for improved results.

## Key findings

- DC reduces depth mixing artifacts.
- Switching to cross-entropy loss improves depth completion.
- Enhanced depth-based object detection performance.

## Abstract

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.