BROWSE
Detail
Conference Paper
Depth Attention Net
Cited 0 time in 
Share 
Share
- Authors
- Hye-Jin S. Kim, Seung-Min Choi, Suyoung Chi
- Issue Date
- 2019-10
- Citation
- International Conference on Information and Communication Technology Convergence (ICTC) 2019, pp.1110-1112
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- Depth estimation has been achieved much attention in recent five years for visual SLAM, AR, VR, autonomous vehicle, 3D object understanding and so on. Similar to stereo matching analysis, stereo image based depth estimation methods using deep learning surprisingly obtain great improvement in performance but still cannot understand why learning depth can estimate depth in a new image and also require accuracy improvement. Therefore, we apply attention mechanism into depth learning. Attention mechanism achieve great improvement in various applications such as visual identification of objects, speech recognition, reasoning, image captioning, summarization, segmentation, machine translation(or NLP) and image classification etc. but yet depth estimation. This is because depth estimation is considered as geometric area. We apply attention mechanism in the PSMNet [1] method. Attention mechanism usually apply to channel attention. In our experiments, we apply our method into two benchmark dataset: KITTI [2] and SceneFlow [3]. In our experiments, we found the attention net can improve the quality of depth.
- KSP Keywords
- 3D object understanding, Attention mechanism, Autonomous vehicle, Benchmark datasets, Depth estimation, Image Classification, Machine Translation(MT), Matching analysis, Visual Identification, Visual SLAM, accuracy improvement