.png){kind=icon}
返回
Graph semantic information for self-supervised monocular depth estimation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.110770.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Self-supervised monocular depth estimation has garnered significant attention in recent years due to its practical value in applications, as it eliminates the need for ground truth depth maps during training. However, its performance usually drops when estimating weakly textured regions and boundary regions, primarily due to the limited depth representation capability of traditional Convolutional Neural Networks (CNNs) that do not support topology. To address these issues, we propose a Graph Semantic Model (GSM) to improve self-supervised monocular depth estimation by utilizing graph learning and semantic information. Our focus is on improving feature representation through graph semantic information. Therefore, we incorporate semantic segmentation and depth estimation into one framework and enhance the interaction of different modal information through the Inter-Directed Graph Reasoning (IDGR) module. In addition, we design the Semantic-Guided Edge Graph Reasoning (SGEGR) module, aiming to boost the network's ability to perceive local depth. Extensive experiments on the KITTI dataset show that our method outperforms the state-of-the-art methods, particularly in accurately estimating depth within weakly textured regions and boundary regions.
Keyword:
Monocular depth estimation
Self-supervision
Convolutional neural networks
Graph learning
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏Learning depth via leveraging semantics: Self-supervised monocular depth estimation with both implicit and explicit semantic guidance.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏HybridNet: Integrating GCN and CNN for skeleton-based action recognitionAPPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏Resolution-sensitive self-supervised monocular absolute depth estimation分辨率敏感的自监督单目绝对深度估计APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏分享收藏Monocular depth estimation with hierarchical fusion of dilated CNNs and soft-weighted-sum inferencePATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏分享收藏 没有更多内容
没有更多内容