Deep neural networks (DNNs) have achieved great success in the area of computer vision. The disparity estimation problem tends to be addressed by DNNs which achieve much better prediction accuracy in stereo matching than traditional hand-crafted feature based methods. On one hand, however, the designed DNNs require significant memory and computation resources to accurately predict the disparity, especially for those 3D convolution based networks, which makes it difficult for deployment in real-time applications. On the other hand, existing computation-efficient networks lack expression capability in large-scale datasets so that they cannot make an accurate prediction in many scenarios. To this end, we propose an efficient and accurate deep network for disparity estimation named FADNet with three main features: 1) It exploits efficient 2D based correlation layers with stacked blocks to preserve fast computation; 2) It combines the residual structures to make the deeper model easier to learn; 3) It contains multi-scale predictions so as to exploit a multi-scale weight scheduling training technique to improve the accuracy. We conduct experiments to demonstrate the effectiveness of FADNet on two popular datasets, Scene Flow and KITTI 2015. Experimental results show that FADNet achieves state-of-the-art prediction accuracy, and runs at a significant order of magnitude faster speed than existing 3D models. The codes of FADNet are available at https://github.com/HKBU-HPML/FADNet.
Fast Implicit Neural Light Field Representation via Geometric Decomposition and Multi-Resolution Low-Rank Features
Institute of Computational Imaging, Beijing Information Science and Technology University(北京信息科技大学计算成像研究所);College of Computer Science (College of Software), Inner Mongolia University(内蒙古大学计算机学院(软件学院))
Depth-Based Selective Blurring in Stereo Images Using Accelerated Framework
National Institute of Technology Karnataka(卡纳塔克邦国家理工学院)
提出了一种基于块和区域的立体匹配方法相结合的立体视差估计方法。它仅从18%图像像素(左或右)的视差测量生成密集的深度图。该方法包括使用快速K-Means实现分割像素亮度值,使用形态滤波和连通分量分析细化分割边界,然后使用绝对差和(SAD)成本函数确定边界的差异。从边界的视差重建完整的视差图。我们考虑我们的方法的应用基于深度的选择性模糊立体图像的非兴趣区域,使用高斯模糊去聚焦用户的非兴趣区域。在Middlebury数据集上的实验表明,该方法比传统的SAD和归一化互相关的视差估计方法提高了33.6%,比一些最近的方法提高了6.1%。此外,我们的方法是高度并行化的使用CPU和GPU框架的基础上Java线程池和APARAPI的速度为5.8 250立体视频帧(4,096 x 2,304)。
Improving Fast Adversarial Training via Self-Knowledge Guidance
School of Cyber Science and Engineering, Southeast University(东南大学网络空间科学与工程学院);City University of Hong Kong(香港城市大学);Purple Mountain Laboratories(紫金山实验室);School of Information Science and Engineering, Ocean University of China(中国海洋大学信息科学与工程学院);University of Macau(澳门大学);Department of Computer Science and Engineering, The Hong Kong University of Science and Technology(香港科技大学计算机科学与工程系)
DensePercept-NCSSD: Vision Mamba towards Real-time Dense Visual Perception with Non-Causal State Space Duality
Machine Intelligence Group, Department of Computer Science & Information Systems, Birla Institute of Technology and Science, Pilani, Hyderabad Campus(机器智能组,计算机科学与信息系统系,比拉理工学院,帕利尼,海得拉巴校区)