Deep Burst Super-Resolution
- URL: http://arxiv.org/abs/2101.10997v1
- Date: Tue, 26 Jan 2021 18:57:21 GMT
- Title: Deep Burst Super-Resolution
- Authors: Goutam Bhat and Martin Danelljan and Luc Van Gool and Radu Timofte
- Abstract summary: 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.
In order to enable training and evaluation on real-world data, we additionally introduce the BurstSR dataset.
- Score: 165.90445859851448
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- A New Dataset and Framework for Real-World Blurred Images Super-Resolution [9.122275433854062]
We develop a new super-resolution dataset specifically tailored for blur images, named the Real-world Blur-kept Super-Resolution (ReBlurSR) dataset.
We propose Perceptual-Blur-adaptive Super-Resolution (PBaSR), which comprises two main modules: the Cross Disentanglement Module (CDM) and the Cross Fusion Module (CFM)
By integrating these two modules, PBaSR achieves commendable performance on both general and blur data without any additional inference and deployment cost.
arXiv Detail & Related papers (2024-07-20T14:07:03Z) - Towards Real-World Burst Image Super-Resolution: Benchmark and Method [93.73429028287038]
In this paper, we establish a large-scale real-world burst super-resolution dataset, i.e., RealBSR, to explore the faithful reconstruction of image details from multiple frames.
We also introduce a Federated Burst Affinity network (FBAnet) to investigate non-trivial pixel-wise displacement among images under real-world image degradation.
arXiv Detail & Related papers (2023-09-09T14:11:37Z) - RBSR: Efficient and Flexible Recurrent Network for Burst
Super-Resolution [57.98314517861539]
Burst super-resolution (BurstSR) aims at reconstructing a high-resolution (HR) image from a sequence of low-resolution (LR) and noisy images.
In this paper, we suggest fusing cues frame-by-frame with an efficient and flexible recurrent network.
arXiv Detail & Related papers (2023-06-30T12:14:13Z) - Gated Multi-Resolution Transfer Network for Burst Restoration and
Enhancement [75.25451566988565]
We propose a novel Gated Multi-Resolution Transfer Network (GMTNet) to reconstruct a spatially precise high-quality image from a burst of low-quality raw images.
Detailed experimental analysis on five datasets validates our approach and sets a state-of-the-art for burst super-resolution, burst denoising, and low-light burst enhancement.
arXiv Detail & Related papers (2023-04-13T17:54:00Z) - Combining Attention Module and Pixel Shuffle for License Plate
Super-Resolution [3.8831062015253055]
This work focuses on license plate (LP) reconstruction in low-resolution and low-quality images.
We present a Single-Image Super-Resolution (SISR) approach that extends the attention/transformer module concept.
In our experiments, the proposed method outperformed the baselines both quantitatively and qualitatively.
arXiv Detail & Related papers (2022-10-30T13:05:07Z) - Learning Enriched Features for Fast Image Restoration and Enhancement [166.17296369600774]
This paper presents a holistic goal of maintaining spatially-precise high-resolution representations through the entire network.
We learn an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details.
Our approach achieves state-of-the-art results for a variety of image processing tasks, including defocus deblurring, image denoising, super-resolution, and image enhancement.
arXiv Detail & Related papers (2022-04-19T17:59:45Z) - RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional
Neural Network [23.451063587138393]
We propose a Raw Burst Super-Resolution Iterative Convolutional Neural Network (RBSRICNN)
The proposed network produces the final output by an iterative refinement of the intermediate SR estimates.
We demonstrate the effectiveness of our proposed approach in quantitative and qualitative experiments.
arXiv Detail & Related papers (2021-10-25T19:01:28Z) - High-resolution Depth Maps Imaging via Attention-based Hierarchical
Multi-modal Fusion [84.24973877109181]
We propose a novel attention-based hierarchical multi-modal fusion network for guided DSR.
We show that our approach outperforms state-of-the-art methods in terms of reconstruction accuracy, running speed and memory efficiency.
arXiv Detail & Related papers (2021-04-04T03:28:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.