Saved in:
Bibliographic Details
Main Authors: Huang, Tingxuan, Miao, Jiacheng, Deng, Shizhuo, Tong, Chen, Dongyue
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.07439
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916542673846272
author Huang, Tingxuan
Miao, Jiacheng
Deng, Shizhuo
Tong
Chen, Dongyue
author_facet Huang, Tingxuan
Miao, Jiacheng
Deng, Shizhuo
Tong
Chen, Dongyue
contents Depth completion is a critical task for handling depth images with missing pixels, which can negatively impact further applications. Recent approaches have utilized Convolutional Neural Networks (CNNs) to reconstruct depth images with the assistance of color images. However, vanilla convolution has non-negligible drawbacks in handling missing pixels. To solve this problem, we propose a new model for depth completion based on an encoder-decoder structure. Our model introduces two key components: the Mask-adaptive Gated Convolution (MagaConv) architecture and the Bi-directional Progressive Fusion (BP-Fusion) module. The MagaConv architecture is designed to acquire precise depth features by modulating convolution operations with iteratively updated masks, while the BP-Fusion module progressively integrates depth and color features, utilizing consecutive bi-directional fusion structures in a global perspective. Extensive experiments on popular benchmarks, including NYU-Depth V2, DIML, and SUN RGB-D, demonstrate the superiority of our model over state-of-the-art methods. We achieved remarkable performance in completing depth maps and outperformed existing approaches in terms of accuracy and reliability.
format Preprint
id arxiv_https___arxiv_org_abs_2401_07439
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mask-adaptive Gated Convolution and Bi-directional Progressive Fusion Network for Depth Completion
Huang, Tingxuan
Miao, Jiacheng
Deng, Shizhuo
Tong
Chen, Dongyue
Computer Vision and Pattern Recognition
Depth completion is a critical task for handling depth images with missing pixels, which can negatively impact further applications. Recent approaches have utilized Convolutional Neural Networks (CNNs) to reconstruct depth images with the assistance of color images. However, vanilla convolution has non-negligible drawbacks in handling missing pixels. To solve this problem, we propose a new model for depth completion based on an encoder-decoder structure. Our model introduces two key components: the Mask-adaptive Gated Convolution (MagaConv) architecture and the Bi-directional Progressive Fusion (BP-Fusion) module. The MagaConv architecture is designed to acquire precise depth features by modulating convolution operations with iteratively updated masks, while the BP-Fusion module progressively integrates depth and color features, utilizing consecutive bi-directional fusion structures in a global perspective. Extensive experiments on popular benchmarks, including NYU-Depth V2, DIML, and SUN RGB-D, demonstrate the superiority of our model over state-of-the-art methods. We achieved remarkable performance in completing depth maps and outperformed existing approaches in terms of accuracy and reliability.
title Mask-adaptive Gated Convolution and Bi-directional Progressive Fusion Network for Depth Completion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.07439