Simple Baselines for Image Restoration

Chen, Liang‐Yu; Chu, Xiaoqing; Zhang, Xiangyu; Sun, Jun

doi:10.48550/arxiv.2204.04676

Cited by 29 publications

(58 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…KPN [69] is a classical network adopting KP which considers the spatially-variant degradation. In addition, we also choose latest NAFNet [70] and HINet [62] because of their excellent performances in various image restoration tasks. We replicate these methods and retrain them on DIVPano with the default setting according to the corresponding papers.…”

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

Annular Computational Imaging: Capture Clear Panoramic Images through Simple Lens

Jiang¹,

Sheng²,

Sun³

et al. 2022

Preprint

View full text Add to dashboard Cite

Panoramic Annular Lens (PAL), composed of few lenses, has great potential in panoramic surrounding sensing tasks for mobile and wearable devices because of its tiny size and large Field of View (FoV). However, the image quality of tiny-volume PAL confines to optical limit due to the lack of lenses for aberration correction. In this paper, we propose an Annular Computational Imaging (ACI) framework to break the optical limit of light-weight PAL design. To facilitate learning-based image restoration, we introduce a wave-based simulation pipeline for panoramic imaging and tackle the synthetic-to-real gap through multiple data distributions. The proposed pipeline can be easily adapted to any PAL with design parameters and is suitable for loose-tolerance designs. Furthermore, we design the Physics Informed Image Restoration Network (PI 2 RNet), considering the physical priors of panoramic imaging and physics-informed learning. At the dataset level, we create the DIVPano dataset and the extensive experiments on it illustrate that our proposed network sets the new state of the art in the panoramic image restoration under spatially-variant degradation. In addition, the evaluation of the proposed ACI on a simple PAL with only 3 spherical lenses reveals the delicate balance between high-quality panoramic imaging and compact design. To the best of our knowledge, we are the first to explore Computational Imaging (CI) in PAL. Code and datasets will be made publicly available at https://github.com/zju-jiangqi/ACI-PI2RNet.

show abstract

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

Annular Computational Imaging: Capture Clear Panoramic Images through Simple Lens

Jiang¹,

Sheng²,

Sun³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…HIT-IIL proposed a NAFNet [4] based model for the RGBW Joint Fusion and Denoise task. As shown in Fig.…”

Section: Hit-iilmentioning

confidence: 99%

“…The final normalization with min=64 and max=1023, with values out of the range clipped. LLCKP proposed a denoising method based on existing image restoration model [14], [4]. As shown in Fig.…”

Section: Jzsherlockmentioning

confidence: 99%

MIPI 2022 Challenge on RGBW Sensor Fusion: Dataset and Report

Yang¹,

Yang²,

Jiang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Developing and integrating advanced image sensors with novel algorithms in camera systems are prevalent with the increasing demand for computational photography and imaging on mobile platforms. However, the lack of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). To bridge the gap, we introduce the first MIPI challenge, including five tracks focusing on novel image sensors and imaging algorithms. In this paper, RGBW Joint Fusion and Denoise, one of the five tracks, working on the fusion of binning-mode RGBW to Bayer, is introduced. The participants were provided with a new dataset including 70 (training) and 15 (validation) scenes of high-quality RGBW and Bayer pairs. In addition, for each scene, RGBW of different noise levels was provided at 24dB and 42dB. All the data were captured using an RGBW sensor in both outdoor and indoor conditions. The final results are evaluated using objective metrics, including PSNR, SSIM [11], LPIPS [15], and KLD. A detailed description of all models developed in this challenge is provided in this paper. More details of this challenge and the link to the dataset can be found at https://github.com/mipi-challenge/MIPI2022

show abstract

“…Recently, with the development of deep learning, numerous image denoising and restoration methods have sprung up like bamboo shoots. For example, DnCNN [2], FFDNet [9], CBDNet [3], RDN [4], NAFNet [10] were proposed successively with increasing denoising ability. These methods are initially proposed for uniform noise, such as Gaussian noise, real image capturing noise.…”

Section: Svqe Modelsmentioning

confidence: 99%

Deep Learning-based Synthesized View Quality Enhancement with DIBR Distortion Mask Prediction Using Synthetic Images

Zhang¹,

Cao²,

Zheng³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recently, deep learning-based image quality enhancement models have been proposed to improve the perceptual quality of distorted synthesized views impaired by compression and Depth Image Based Rendering (DIBR) process in multiview video systems. However, due to the lack of multi-view video plus depth data, the training data for quality enhancement models is small, which limits the performance and progress of these models. Augmenting the training data to enhance the Synthesized View Quality Enhancement (SVQE) models is a feasible solution. In this paper, we suggest a deep learning-based SVQE model using more synthetic Synthesized View Images (SVIs). To simulate the irregular geometric displacement of DIBR distortion, a random irregular polygon-based SVI synthesis method is proposed based on existing massive RGB/RGBD data, and a synthetic synthesized view database is constructed, which includes synthetic SVIs and DIBR distortion masks. Moreover, to further guide the SVQE models to focus more precisely on DIBR distortion, the DIBR distortion mask prediction network which could predict the position and variance of DIBR distortion is embedded into the SVQE models. The experimental results demonstrate that by pretraining on the synthetic SVI database, the performance of the existing SVQE models could be greatly promoted. In addition, by introducing the DIBR distortion mask prediction network, the SVI quality could be further enhanced.

show abstract

Simple Baselines for Image Restoration

Cited by 29 publications

References 0 publications

Annular Computational Imaging: Capture Clear Panoramic Images through Simple Lens

Annular Computational Imaging: Capture Clear Panoramic Images through Simple Lens

MIPI 2022 Challenge on RGBW Sensor Fusion: Dataset and Report

Deep Learning-based Synthesized View Quality Enhancement with DIBR Distortion Mask Prediction Using Synthetic Images

Contact Info

Product

Resources

About