Seeing Motion in the Dark

Abstract

Deep learning has recently been applied with impressive results to extreme low-light imaging. Despite the success of single image processing, extreme low-light video processing is still intractable due to the difficulty to collect raw video data as well as their corresponding ground truth. Common strategy of taking long-exposure ground truth in single imaging is not feasible for videos. In this paper, we present deep processing of very dark raw videos: on the order of one lux of illuminance. To support this line of work, we collect a new dataset of raw low-light videos, in which high-resolution raw data is captured at video rate. At this level of darkness, the signal-to-noise ratio is extremely low (negative if measured in dB) and traditional image processing pipeline generally breaks down. A new method is presented to address this challenging problem. By carefully designing a learning-based pipeline and introducing a new loss function to encourage temporal stability, we train a siamese network on static raw videos, for which ground truth is available, such that the network generalizes to videos of dynamic scenes at test time. Experimental results demonstrate that the presented approach outperforms state-of-the-art models for burst processing, per-frame processing, and blind temporal consistency.

Materials