IEEE Sensors Journal · 2023 · 11 citations · 22 references
ComputingComputer ScienceAutonomous VehiclesComputer VisionVisual AttentionDeep LearningDepth EstimationFeature-based AttentionRobotic VisionScene UnderstandingConvolutional Neural NetworksLong-range Dependency ModelingMonocular Depth EstimationVision Sensors
Depth estimation using monocular vision sensors is crucial in computer vision, with diverse applications ranging from autonomous driving to robot motion. Conventional methods suffer from the trade-off between consistency and fine-grained details due to the local-receptive field limiting their practicality. This lack of long-range dependency inherently comes from the convolutional neural network (CNN) part of the architecture. In this article, a dual window transformer-based network, namely DwinFormer, is proposed, which utilizes both local and global features for depth estimation using monocular vision sensors. The DwinFormer consists of dual window self-attention (Dwin-SA) and cross-attention transformers, dual window self-attention transformer (Dwin-SAT) and dual window cross attention transformer (Dwin-CAT), respectively. The Dwin-SAT seamlessly extracts intricate, locally aware features while concurrently capturing global context. It harnesses the power of local and global window attention to adeptly capture both short-range and long-range dependencies, obviating the need for complex and computationally expensive operations, such as attention masking or window shifting. Moreover, Dwin-SAT introduces inductive biases which provide desirable properties, such as translational equivariance and less dependence on large-scale data. Furthermore, conventional decoding methods often rely on skip connections which may result in semantic discrepancies and a lack of global context when fusing encoder and decoder features. In contrast, the Dwin-CAT employs both local and global window cross-attention to seamlessly fuse encoder and decoder features with both fine-grained local and contextually aware global information, effectively amending semantic gap. Empirical evidence obtained through extensive experimentation on the NYU-Depth-V2 and Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) datasets demonstrates the superiority of the proposed method, consistently outperforming existing approaches across both indoor and outdoor environments.
22
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2017 · 22.1K citations
Vision meets robotics: The KITTI dataset
Andreas Geiger, Philip Lenz, Christoph Stiller et al. · The International Journal of Robotics Research · 2013 · 9.7K citations
Zhuang Liu, Hanzi Mao, Chao-Yuan Wu et al. · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2022 · 7.1K citations