DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image

12/02/2018
by   Jiaxiong Qiu, et al.
0

In this paper, we propose a deep learning architecture that produces accurate dense depth for the outdoor scene from a single color image and a sparse depth. Inspired by the indoor depth completion, our network estimates surface normals as the intermediate representation to produce dense depth, and can be trained end-to-end. With a modified encoder-decoder structure, our network effectively fuses the dense color image and the sparse LiDAR depth. To address outdoor specific challenges, our network predicts a confidence mask to handle mixed LiDAR signals near foreground boundaries due to occlusion, and combines estimates from the color image and surface normals with learned attention maps to improve the depth accuracy especially for distant areas. Extensive experiments demonstrate that our model improves upon the state-of-the-art performance on KITTI depth completion benchmark. Ablation study shows the positive impact of each model components to the final performance, and comprehensive analysis shows that our model generalizes well to the input with higher sparsity or from indoor scenes.

READ FULL TEXT

page 1

page 3

page 4

page 6

page 7

research
10/15/2019

Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints

Depth completion aims to recover dense depth maps from sparse depth meas...
research
11/27/2017

Depth Map Completion by Jointly Exploiting Blurry Color Images and Sparse Depth Maps

We aim at predicting a complete and high-resolution depth map from incom...
research
04/06/2021

Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries

Depth completion starts from a sparse set of known depth values and esti...
research
03/02/2023

DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction

We present DejaVu, a novel framework which leverages conditional image r...
research
10/26/2022

CU-Net: LiDAR Depth-Only Completion With Coupled U-Net

LiDAR depth-only completion is a challenging task to estimate dense dept...
research
03/15/2020

Scene Completenesss-Aware Lidar Depth Completion for Driving Scenario

In this paper we propose Scene Completeness-Aware Depth Completion (SADC...
research
03/15/2020

Scene Completeness-Aware Lidar Depth Completion for Driving Scenario

In this paper we propose Scene Completeness-Aware Depth Completion (SADC...

Please sign up or login with your details

Forgot password? Click here to reset