.png){kind=icon}
返回
Robust depth completion based on Semantic Aggregation
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-024-05366-5.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Guided by information from RGB images, depth completion methods rebuild the dense depth from sparse depth input. However, the varying densities of valid pixels in sparse depth maps pose a significant challenge to the robustness of the completion model. To improve the robustness of depth completion, we propose a two-stage model called Semantic Aggregated Depth Completion (SADC) in this paper, comprising a coarse-grained completion stage and a fine-grained completion stage. In the coarse-grained completion stage, the Semantic Extraction Network (SEN) extracts RGB features and sends them to the Dynamic Semantic Aggregation (DSA) to predict the local semantic relationship (LSR) matrix. DSA aggregates the valid information based on the LSR matrix iteratively, resulting in coarse-grained completion results. In the fine-grained completion stage, SADC uses the Semantic Guidance Network (SGN) and Semantic Guidance Fusion (SGF) modules to refine the dense depth features from coarse-grained completion results by RGB features in multi-level and predict fine-grained completion results. We validate our method on NYU-v2 and KITTI with different valid pixel densities. The results demonstrate that SADC performs best results on benchmark tests and exhibits robustness to different densities without retraining.
Keyword:
RGB-D vision
Depth completion
Depth estimation
Depth reconstruction
Multi-modal fusion
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Seismic profiles of the offshore Gulf of Alaska Tertiary Province, R/V Thompson, Sept.-Oct. 1974
OAAI
OAAI分享收藏Depth scale balance saliency detection with connective feature pyramid and edge guidance.png)
APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏Promoting Monocular Depth Estimation by Multi-Scale Residual Laplacian Pyramid Fusion多尺度残差拉普拉斯金字塔融合促进单目深度估计
PREAI
分享收藏
查看更多内容