LatentBurst: A Fast and Efficient Multi Frame Super-Resolution for Hexadeca-Bayer Pattern CIS images

TL;DR

This paper presents LatentBurst, a fast multi-frame super-resolution network for hexadeca-Bayer CIS images, addressing demosaicing, denoising, and fusion challenges for real-time mobile device applications.

Contribution

The paper introduces a novel, efficient network architecture with pyramid alignment and knowledge distillation tailored for hexadeca-Bayer pattern super-resolution.

Findings

Outperforms state-of-the-art methods in various scenarios

Operates in real-time on mobile devices

Effectively handles large motion and misalignment

Abstract

This paper introduces a novel multi frame super-resolution network (MFSR) for burst hexadeca Bayer pattern Contact Image Sensor (CIS) images, which includes demosaicing, denoising, multi-frame fusion, and super-resolution. Designing a high-quality reconstruction network poses several challenges as follows: 1) Unlike the Bayer color filter array (CFA) pattern, it is hard to interpolate hexadeca-Bayer pattern since the pixel distance between the same color groups increases; 2) Due to large object motion and camera movements, the final fusion result usually suffers the misalignment resulting a blurry image or ghosting artifacts; 3) The proposed network should be fast and efficient enough to operate in real-time on mobile devices. To overcome these challenges, we propose a novel network, called LatentBurst, which contains: 1) a pyramid align and fusion approach in latent feature to deal with large motion scenario; 2) an efficient UNet-based structure which can run efficiently on mobile device; 3) fine-tuned optical flow estimation and two-step knowledge distillation to reduce domain-gap more effectively. Experimental results in various scenarios demonstrate the effectiveness of our proposed method compared with other state-of-the-art methods.