A Dual Camera System for High Spatiotemporal Resolution Video Acquisition

TL;DR

This paper introduces a dual camera system and an end-to-end learning framework to synthesize high spatiotemporal resolution videos by combining inputs from cameras with different resolutions and frame rates, validated on real and simulated data.

Contribution

The paper proposes AWnet, an innovative end-to-end learning framework with adaptive pixel-wise weighting for combining dual camera videos to produce high-quality HSTR videos, including noise regularization for real-world robustness.

Findings

Demonstrated improved PSNR in simulations across multiple datasets.

Achieved high-quality HSTR videos from real dual-camera setups.

Conducted ablation studies to analyze system capabilities.

Abstract

This paper presents a dual camera system for high spatiotemporal resolution (HSTR) video acquisition, where one camera shoots a video with high spatial resolution and low frame rate (HSR-LFR) and another one captures a low spatial resolution and high frame rate (LSR-HFR) video. Our main goal is to combine videos from LSR-HFR and HSR-LFR cameras to create an HSTR video. We propose an end-to-end learning framework, AWnet, mainly consisting of a FlowNet and a FusionNet that learn an adaptive weighting function in pixel domain to combine inputs in a frame recurrent fashion. To improve the reconstruction quality for cameras used in reality, we also introduce noise regularization under the same framework. Our method has demonstrated noticeable performance gains in terms of both objective PSNR measurement in simulation with different publicly available video and light-field datasets and subjective evaluation with real data captured by dual iPhone 7 and Grasshopper3 cameras. Ablation studies are further conducted to investigate and explore various aspects (such as reference structure, camera parallax, exposure time, etc) of our system to fully understand its capability for potential applications.