ReconfigISP: Reconfigurable Camera Image Processing Pipeline
This addresses the need for adaptable camera image processing pipelines in real-world applications, representing a novel method for a known bottleneck rather than an incremental improvement.
The authors tackled the problem of fixed ISP architectures being suboptimal for diverse camera sensors, scenes, and tasks by proposing ReconfigISP, a reconfigurable ISP that automatically tailors its architecture and parameters to specific data and tasks, achieving effectiveness in image restoration and object detection with only hundreds of parameters per task.
Image Signal Processor (ISP) is a crucial component in digital cameras that transforms sensor signals into images for us to perceive and understand. Existing ISP designs always adopt a fixed architecture, e.g., several sequential modules connected in a rigid order. Such a fixed ISP architecture may be suboptimal for real-world applications, where camera sensors, scenes and tasks are diverse. In this study, we propose a novel Reconfigurable ISP (ReconfigISP) whose architecture and parameters can be automatically tailored to specific data and tasks. In particular, we implement several ISP modules, and enable backpropagation for each module by training a differentiable proxy, hence allowing us to leverage the popular differentiable neural architecture search and effectively search for the optimal ISP architecture. A proxy tuning mechanism is adopted to maintain the accuracy of proxy networks in all cases. Extensive experiments conducted on image restoration and object detection, with different sensors, light conditions and efficiency constraints, validate the effectiveness of ReconfigISP. Only hundreds of parameters need tuning for every task.