Deep Reparametrization of Multi-Frame Super-Resolution and Denoising

  title={Deep Reparametrization of Multi-Frame Super-Resolution and Denoising},
  author={Goutam Bhat and Martin Danelljan and Fisher Yu and Luc Van Gool and Radu Timofte},
  journal={2021 IEEE/CVF International Conference on Computer Vision (ICCV)},
We propose a deep reparametrization of the maximum a posteriori formulation commonly employed in multi-frame image restoration tasks. Our approach is derived by introducing a learned error metric and a latent representation of the target image, which transforms the MAP objective to a deep feature space. The deep reparametrization allows us to directly model the image formation process in the latent space, and to integrate learned image priors into the prediction. Our approach thereby leverages… 
BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment
This work addresses the Burst Super-Resolution (BurstSR) task using a new architecture, which requires restoring a high-quality image from a sequence of noisy, misaligned, and low-resolution RAW bursts, and proposes a Pyramid Flow-Guided Deformable Convolution Network (Pyramid FG-DCN) and incorporate Swin Transformer Blocks and Groups as the main backbone.
Kernel-aware Raw Burst Blind Super-Resolution
A kernel-guided strategy which can solve the burst SR with two steps: kernel modeling and HR restoring, and a kernel-aware deformable alignment module which can effectively align the raw images with consideration of the blurry priors.
Uncertainty-Aware Cascaded Dilation Filtering for High-Efficiency Deraining
A simple yet efficient deraining method is proposed by formulating deraining as a predictive filtering problem without complex rain model assumptions that outperforms baseline methods on four single-image deraining datasets and one video deraining dataset in terms of both recovery quality and speed.
Burst Image Restoration and Enhancement
In comparison to existing works that usually follow a late fusion scheme with single-stage upsampling, this approach performs favorably, delivering state-of-the-art performance on burst super-resolution, burst low-light image enhancement and burst denoising tasks.
NAN: Noise-Aware NeRFs for Burst-Denoising
It is shown that Neural Radiance Fields (NeRFs), originally suggested for physics-based novel-view rendering, can serve as a powerful framework for burst denoising and is especially successful in coping with large movement and occlusions, under very high levels of noise.


Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising Networks
This work proposes a novel deep learning architecture which is inspired by powerful classical image regularization methods and large-scale convex optimization techniques, and shows that the network has the ability to generalize well even when it is trained on small datasets, while keeping the overall number of trainable parameters low.
Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
This paper proposes the Laplacian Pyramid Super-Resolution Network (LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images and generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications.
Recurrent Back-Projection Network for Video Super-Resolution
We proposed a novel architecture for the problem of video super-resolution. We integrate spatial and temporal contexts from continuous video frames using a recurrent encoder-decoder module, that
Enhanced Deep Residual Networks for Single Image Super-Resolution
This paper develops an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods, and proposes a new multi-scale deepsuper-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model.
Learning a Deep Convolutional Network for Image Super-Resolution
This work proposes a deep learning method for single image super-resolution (SR) that directly learns an end-to-end mapping between the low/high-resolution images and shows that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.
Deep Unfolding Network for Image Super-Resolution
This paper proposes an end-to-end trainable unfolding network which leverages both learningbased methods and model-based methods to super-resolve blurry, noisy images for different scale factors via a single model, while maintaining the advantages of learning- based methods.
Iterative Residual CNNs for Burst Photography Applications
This work focuses on the fact that every frame of a burst sequence can be accurately described by a forward (physical) model, which allows us to restore a single image of higher quality from a sequence of low-quality images as the solution of an optimization problem.
Deep learning for fast super-resolution reconstruction from multiple images
This work explores how to exploit CNNs in multiple-image SRR and demonstrates that competitive reconstruction outcome can be obtained within seconds.
HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery
HighRes-net is presented, the first deep learning approach to MFSR that learns its sub-tasks in an end-to-end fashion, and shows that by learning deep representations of multiple views, it can super-resolve low-resolution signals and enhance Earth Observation data at scale.
Residual Dense Network for Image Super-Resolution
This paper proposes residual dense block (RDB) to extract abundant local features via dense connected convolutional layers and uses global feature fusion in RDB to jointly and adaptively learn global hierarchical features in a holistic way.