Learning Enriched Features for Real Image Restoration and Enhancement

@article{Zamir2020LearningEF,
  title={Learning Enriched Features for Real Image Restoration and Enhancement},
  author={Syed Waqas Zamir and Aditya Arora and Salman Hameed Khan and Munawar Hayat and Fahad Shahbaz Khan and Ming-Hsuan Yang and Ling Shao},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.06792}
}
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing. Recently, convolutional neural networks (CNNs) have achieved dramatic improvements over conventional approaches for image restoration task. Existing CNN-based methods typically operate either on full-resolution or on progressively low-resolution representations. In the former… Expand
NBNet: Noise Basis Learning for Image Denoising with Subspace Projection
TLDR
This paper proposes SSA, a non-local subspace attention module designed explicitly to learn the basis generation as well as the subspace projection, and incorporates SSA with NBNet, a UNet structured network designed for end-to-end image denosing. Expand
Feature-Align Network and Knowledge Distillation for Efficient Denoising
TLDR
A novel network for efficient RAW denoising on mobile devices augmented with a new Feature-Align layer to attend to spatially varying noise and a new perceptual Feature Loss calculated in the RAW domain to preserve high frequency image content is proposed. Expand
Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes
TLDR
This paper considers matching images of low-light scenes, aiming to widen the frontier of SfM and visual SLAM applications and shows the advantage of using the RAW-format images and the strengths and weaknesses of the above component methods. Expand
Pseudo 3D Auto-Correlation Network for Real Image Denoising
TLDR
A pseudo 3D auto-correlation network (P3AN) is proposed to explore a more efficient way of capturing contextual information in image denoising and shows great superiority and surpasses state-of-the-art image Denoising methods. Expand
Restore from Restored: Single Image Denoising with Pseudo Clean Image
TLDR
A simple and effective fine-tuning algorithm called "restore-from-restored", which can greatly enhance the performance of fully pre-trained image denoising networks and further improve the performance on numerous Denoising benchmark datasets including real noisy images. Expand
Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement
  • Chuanjun Zheng, Daming Shi, Wentian Shi
  • Engineering, Computer Science
  • 2021
TLDR
An adaptive unfolding total variation network (UTVNet) is proposed, which approximates the noise level from the real sRGB low-light image by learning the balancing parameter in the model-based denoising method with total variation regularization and unrolling the corresponding minimization process for providing the inferences of smoothness and fidelity constraints. Expand
Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement
TLDR
A novel two-step generation network for degradation learning and content refinement that is not only superior to one-step methods, but also is capable of synthesizing sufficient paired samples to benefit the model training. Expand
Progressive Joint Low-light Enhancement and Noise Removal for Raw Images
TLDR
A low-light image processing framework that performs joint illumination adjustment, color enhancement, and denoising and does not need to recollect massive data when being adapted to another camera model, which significantly reduces the efforts required to fine-tune the approach for practical usage. Expand
Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References
TLDR
A neural network for multi-level low-light image enhancement, which is userfriendly to meet various requirements by selecting different images as brightness reference by decomposing an image into two low-coupling feature components in the latent space, which allows the concatenation feasibility of the content components from low- light images and the luminance components from reference images. Expand
Uformer: A General U-Shaped Transformer for Image Restoration
TLDR
Uformer is presented, an effective and efficient Transformer-based architecture, in which a hierarchical encoder-decoder network is built using the Transformer block for image restoration, and three skip-connection schemes are explored to effectively deliver information from the encoder to the decoder. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 138 REFERENCES
Deep Retinex Decomposition for Low-Light Enhancement
TLDR
Extensive experiments demonstrate that the proposed deep Retinex-Net learned on this LOw-Light dataset not only achieves visually pleasing quality for low-light enhancement but also provides a good representation of image decomposition. Expand
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
TLDR
This paper investigates the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image Denoising, and uses residual learning and batch normalization to speed up the training process as well as boost theDenoising performance. Expand
Toward Real-World Single Image Super-Resolution: A New Benchmark and a New Model
TLDR
This paper builds a real-world super-resolution (RealSR) dataset where paired LR-HR images on the same scene are captured by adjusting the focal length of a digital camera and presents a Laplacian pyramid based kernel prediction network (LP-KPN), which efficiently learns per-pixel kernels to recover the HR image. Expand
Underexposed Photo Enhancement Using Deep Illumination Estimation
TLDR
A new neural network for enhancing underexposed photos is presented, which introduces intermediate illumination in its network to associate the input with expected enhancement result, which augments the network's capability to learn complex photographic adjustment from expert-retouched input/output image pairs. Expand
A High-Quality Denoising Dataset for Smartphone Cameras
TLDR
This paper proposes a systematic procedure for estimating ground truth for noisy images that can be used to benchmark denoising performance for smartphone cameras and shows that CNN-based methods perform better when trained on the authors' high-quality dataset than when trained using alternative strategies, such as low-ISO images used as a proxy for ground truth data. Expand
Benchmarking Denoising Algorithms with Real Photographs
  • Tobias Plötz, S. Roth
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
This work develops a methodology for benchmarking denoising techniques on real photographs, and captures pairs of images with different ISO values and appropriately adjusted exposure times, where the nearly noise-free low-ISO image serves as reference. Expand
Learning photographic global tonal adjustment with a database of input/output image pairs
TLDR
This work creates a high-quality reference dataset, collects 5,000 photos, manually annotated them, and hired 5 trained photographers to retouch each picture, and introduces difference learning: this method models and predicts difference between users. Expand
Real Image Denoising With Feature Attention
  • Saeed Anwar, N. Barnes
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
TLDR
A novel single-stage blind real image denoising network (RIDNet) is proposed by employing a modular architecture that uses residual on the residual structure to ease the flow of low-frequency information and apply feature attention to exploit the channel dependencies. Expand
Selective Kernel Networks
TLDR
Detailed analyses show that the neurons in SKNet can capture target objects with different scales, which verifies the capability of neurons for adaptively adjusting their receptive field sizes according to the input. Expand
Toward Convolutional Blind Denoising of Real Photographs
TLDR
A convolutional blind denoising network (CBDNet) with more realistic noise model and real-world noisy-clean image pairs and a noise estimation subnetwork with asymmetric learning to suppress under-estimation of noise level is embedded into CBDNet. Expand
...
1
2
3
4
5
...