Spike Camera
Spike cameras are high-speed visual sensors that record asynchronous photon events as spike streams, offering advantages in high-dynamic range and temporal resolution over traditional frame-based cameras. Current research focuses on developing algorithms and models, such as SpikeNeRF and SwinSF, for image reconstruction, 3D scene reconstruction (using techniques like 3D Gaussian splatting), and novel view synthesis from these spike streams, often addressing challenges like motion blur and noise. This technology holds significant promise for applications requiring high-speed imaging and precise temporal information, impacting fields like autonomous driving, robotics, and biomedical imaging.
Papers
Uncertainty Guided Depth Fusion for Spike Camera
Jianing Li, Jiaming Liu, Xiaobao Wei, Jiyuan Zhang, Ming Lu, Lei Ma, Li Du, Tiejun Huang, Shanghang Zhang
Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer
Jiaming Liu, Qizhe Zhang, Jianing Li, Ming Lu, Tiejun Huang, Shanghang Zhang