Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data

TL;DR

This paper introduces a domain adaptation method for depth completion that trains on synthetic data and effectively handles real sensor noise, improving performance without requiring real annotations.

Contribution

It presents a novel domain adaptation framework that simulates real sensor noise and adapts synthetic data for depth completion, enabling training without real domain annotations.

Findings

Significant performance improvements on KITTI benchmark

Effective simulation of real sensor noise in synthetic data

Enhanced depth completion accuracy without real annotations

Abstract

Depth completion aims to predict a dense depth map from a sparse depth input. The acquisition of dense ground truth annotations for depth completion settings can be difficult and, at the same time, a significant domain gap between real LiDAR measurements and synthetic data has prevented from successful training of models in virtual settings. We propose a domain adaptation approach for sparse-to-dense depth completion that is trained from synthetic data, without annotations in the real domain or additional sensors. Our approach simulates the real sensor noise in an RGB+LiDAR set-up, and consists of three modules: simulating the real LiDAR input in the synthetic domain via projections, filtering the real noisy LiDAR for supervision and adapting the synthetic RGB image using a CycleGAN approach. We extensively evaluate these modules against the state-of-the-art in the KITTI depth completion benchmark, showing significant improvements.