.png){kind=icon}
返回
CMVDE: Consistent Multi-View Video Depth Estimation via Geometric-Temporal Coupling Approach
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2024.3397080.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In the field of video depth estimation, significant strides have been made with deep learning-based multi-view stereo approaches. However, existing studies struggle to produce consistently accurate depth maps that account for both multi-view geometry and temporal consistency from monocular video contents. To overcome this limitation, we introduce CMVDE, an innovative video depth estimation framework that leverages a multi-view geometric-temporal coupling approach in an end-to-end manner. Our proposed geometric consistency module efficiently generates multi-view geometric features by employing mutual cross-view epipolar attention between adjacent video frames. Additionally, it compresses these features using the novel multi-scale feature compressor, producing an effective input tensor for the subsequent module. Moreover, our framework enhances temporal consistency across consecutive video frames with the temporal consistency module based on convolutional LSTM [1] leveraging previous depth information as geometric guidance. Compared to state-of-the-art models, our approach achieves superior performance in depth quality and consecutive consistency on the ScanNet [2] and 7-Scenes [3] datasets, surpassing previous multi-view video depth estimation methods.
Keyword:
Estimation
Feature extraction
Costs
Three-dimensional displays
Geometry
Couplings
Computational efficiency
Epipolar attention
multi-view stereo
multi-view geometric-temporal coupling
video depth estimation
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
.png){kind=icon}
Prediction of Smoke Propagation in a Big Multi-Story Building Using Fire Dynamics Simulator (FDS)
OAAI
OAAI分享收藏分享收藏
查看更多内容