Deep Burst Super-Resolution

TL;DR

This paper introduces a novel multi-frame super-resolution architecture that leverages multiple burst images and an attention-based fusion mechanism to produce high-quality, super-resolved RGB images, validated on a new real-world dataset.

Contribution

The paper presents a new burst super-resolution network with explicit alignment and adaptive fusion, along with the BurstSR dataset for real-world training and evaluation.

Findings

Effective alignment of deep embeddings using optical flow.

Superior super-resolution results on real-world smartphone data.

Demonstrated robustness and improved quality over existing methods.

Abstract

While single-image super-resolution (SISR) has attracted substantial interest in recent years, the proposed approaches are limited to learning image priors in order to add high frequency details. In contrast, multi-frame super-resolution (MFSR) offers the possibility of reconstructing rich details by combining signal information from multiple shifted images. This key advantage, along with the increasing popularity of burst photography, have made MFSR an important problem for real-world applications. We propose a novel architecture for the burst super-resolution task. Our network takes multiple noisy RAW images as input, and generates a denoised, super-resolved RGB image as output. This is achieved by explicitly aligning deep embeddings of the input frames using pixel-wise optical flow. The information from all frames are then adaptively merged using an attention-based fusion module. In order to enable training and evaluation on real-world data, we additionally introduce the BurstSR dataset, consisting of smartphone bursts and high-resolution DSLR ground-truth. We perform comprehensive experimental analysis, demonstrating the effectiveness of the proposed architecture.