Towards Fast and Light-Weight Restoration of Dark Images

• URL: http://arxiv.org/abs/2011.14133v1
• Date: Sat, 28 Nov 2020 13:53:50 GMT
• Title: Towards Fast and Light-Weight Restoration of Dark Images
• Authors: Mohit Lamba and Atul Balaji and Kaushik Mitra
• Abstract summary: We show that we can enhance a full resolution, 2848 x 4256, extremely dark single-image in the ballpark of 3 seconds even on a CPU. We achieve this with 2 - 7x fewer model parameters, 2 - 3x lower memory utilization, 5 - 20x speed up and yet maintain a competitive image reconstruction quality.
• Score: 26.779714419544085
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The ability to capture good quality images in the dark and near-zero lux conditions has been a long-standing pursuit of the computer vision community. The seminal work by Chen et al. [5] has especially caused renewed interest in this area, resulting in methods that build on top of their work in a bid to improve the reconstruction. However, for practical utility and deployment of low-light enhancement algorithms on edge devices such as embedded systems, surveillance cameras, autonomous robots and smartphones, the solution must respect additional constraints such as limited GPU memory and processing power. With this in mind, we propose a deep neural network architecture that aims to strike a balance between the network latency, memory utilization, model parameters, and reconstruction quality. The key idea is to forbid computations in the High-Resolution (HR) space and limit them to a Low-Resolution (LR) space. However, doing the bulk of computations in the LR space causes artifacts in the restored image. We thus propose Pack and UnPack operations, which allow us to effectively transit between the HR and LR spaces without incurring much artifacts in the restored image. We show that we can enhance a full resolution, 2848 x 4256, extremely dark single-image in the ballpark of 3 seconds even on a CPU. We achieve this with 2 - 7x fewer model parameters, 2 - 3x lower memory utilization, 5 - 20x speed up and yet maintain a competitive image reconstruction quality compared to the state-of-the-art algorithms.

Related papers

• DarkShot: Lighting Dark Images with Low-Compute and High-Quality [11.256790804961563]
  This paper proposes a lightweight network that outperforms existing state-of-the-art (SOTA) methods in low-light enhancement tasks. Our model can restore a UHD 4K resolution image with minimal computation while keeping SOTA restoration quality.
  arXiv  Detail & Related papers  (2023-12-28T03:26:50Z)
• Real-time 6K Image Rescaling with Rate-distortion Optimization [53.61374658914277]
  We propose a novel framework for real-time 6K rate-distortion-aware image rescaling. Our framework embeds an HR image into a JPEG LR thumbnail by an encoder. Then, an efficient frequency-aware decoder reconstructs a high-fidelity HR image from the LR one in real time.
  arXiv  Detail & Related papers  (2023-04-03T15:21:56Z)
• Perceptual Image Enhancement for Smartphone Real-Time Applications [60.45737626529091]
  We propose LPIENet, a lightweight network for perceptual image enhancement. Our model can deal with noise artifacts, diffraction artifacts, blur, and HDR overexposure. Our model can process 2K resolution images under 1 second in mid-level commercial smartphones.
  arXiv  Detail & Related papers  (2022-10-24T19:16:33Z)
• BSRA: Block-based Super Resolution Accelerator with Hardware Efficient Pixel Attention [0.10547353841674209]
  This paper proposes a super resolution hardware accelerator with hardware efficient pixel attention. The final implementation can support full HD image reconstruction at 30 frames per second with TSMC 40nm CMOS process.
  arXiv  Detail & Related papers  (2022-05-02T09:56:29Z)
• NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction [50.54946139497575]
  We propose NeRFusion, a method that combines the advantages of NeRF and TSDF-based fusion techniques to achieve efficient large-scale reconstruction and photo-realistic rendering. We demonstrate that NeRFusion achieves state-of-the-art quality on both large-scale indoor and small-scale object scenes, with substantially faster reconstruction than NeRF and other recent methods.
  arXiv  Detail & Related papers  (2022-03-21T18:56:35Z)
• Spatially-Adaptive Image Restoration using Distortion-Guided Networks [51.89245800461537]
  We present a learning-based solution for restoring images suffering from spatially-varying degradations. We propose SPAIR, a network design that harnesses distortion-localization information and dynamically adjusts to difficult regions in the image.
  arXiv  Detail & Related papers  (2021-08-19T11:02:25Z)
• SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network [6.722629246312285]
  We propose a generative adversarial network-based reconstruction framework for single-pixel imaging, referred to as SPI-GAN. Our method can reconstruct images with 17.92 dB PSNR and 0.487 SSIM, even if the sampling ratio drops to 5%.
  arXiv  Detail & Related papers  (2021-07-03T03:06:09Z)
• Exploiting Raw Images for Real-Scene Super-Resolution [105.18021110372133]
  We study the problem of real-scene single image super-resolution to bridge the gap between synthetic data and real captured images. We propose a method to generate more realistic training data by mimicking the imaging process of digital cameras. We also develop a two-branch convolutional neural network to exploit the radiance information originally-recorded in raw images.
  arXiv  Detail & Related papers  (2021-02-02T16:10:15Z)
• CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing [84.92009553462384]
  We propose a NOVEL pixel translation framework called Cooperative GAN(CooGAN) for HR facial image editing. This framework features a local path for fine-grained local facial patch generation (i.e., patch-level HR, LOW memory) and a global path for global lowresolution (LR) facial structure monitoring (i.e., image-level LR, LOW memory) In addition, we propose a lighter selective transfer unit for more efficient multi-scale features fusion, yielding higher fidelity facial attributes manipulation.
  arXiv  Detail & Related papers  (2020-11-03T08:40:00Z)
• Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting [12.839962012888199]
  We propose a Contextual Residual Aggregation (CRA) mechanism that can produce high-frequency residuals for missing contents. CRA mechanism produces high-frequency residuals for missing contents by weighted aggregating residuals from contextual patches. We train the proposed model on small images with resolutions 512x512 and perform inference on high-resolution images, achieving compelling inpainting quality.
  arXiv  Detail & Related papers  (2020-05-19T18:55:32Z)
• Perceptual Image Super-Resolution with Progressive Adversarial Network [17.289101902846358]
  Single Image Super-Resolution (SISR) aims to improve resolution of small-size low-quality image from a single one. In this paper, we argue that the curse of dimensionality is the underlying reason of limiting the performance of state-of-the-art algorithms. We propose Progressive Adversarial Network (PAN) that is capable of coping with this difficulty for domain-specific image super-resolution.
  arXiv  Detail & Related papers  (2020-03-08T10:19:34Z)

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.