MSS-DepthNet: Depth Prediction with Multi-Step Spiking Neural Network
This work addresses the problem of handling asynchronous, sparse event streams for depth prediction in computer vision and robotics, representing an incremental advancement by combining existing SNN concepts with novel architectural components.
The paper tackles depth prediction from event camera data by proposing a spiking neural network architecture with a novel residual block and multi-dimension attention modules, along with a new event stream representation method, achieving improved performance over previous ANN networks of the same size on the MVSEC dataset and demonstrating high computational efficiency.
Event cameras are considered to have great potential for computer vision and robotics applications because of their high temporal resolution and low power consumption characteristics. However, the event stream output from event cameras has asynchronous, sparse characteristics that existing computer vision algorithms cannot handle. Spiking neural network is a novel event-based computational paradigm that is considered to be well suited for processing event camera tasks. However, direct training of deep SNNs suffers from degradation problems. This work addresses these problems by proposing a spiking neural network architecture with a novel residual block designed and multi-dimension attention modules combined, focusing on the problem of depth prediction. In addition, a novel event stream representation method is explicitly proposed for SNNs. This model outperforms previous ANN networks of the same size on the MVSEC dataset and shows great computational efficiency.