D2C-SR: A Divergence to Convergence Approach for Image Super-Resolution
- URL: http://arxiv.org/abs/2103.14373v1
- Date: Fri, 26 Mar 2021 10:20:28 GMT
- Title: D2C-SR: A Divergence to Convergence Approach for Image Super-Resolution
- Authors: Youwei Li, Haibin Huang, Lanpeng Jia, Haoqiang Fan and Shuaicheng Liu
- Abstract summary: We present D2C-SR, a novel framework for the task of image super-resolution(SR)
Inspired by recent works like SRFlow, we tackle this problem in a semi-probabilistic manner.
Our experiments demonstrate that D2C-SR can achieve state-of-the-art performance on PSNR and SSIM, with a significantly less computational cost.
- Score: 25.17545119739454
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this paper, we present D2C-SR, a novel framework for the task of image
super-resolution(SR). As an ill-posed problem, the key challenge for
super-resolution related tasks is there can be multiple predictions for a given
low-resolution input. Most classical methods and early deep learning based
approaches ignored this fundamental fact and modeled this problem as a
deterministic processing which often lead to unsatisfactory results. Inspired
by recent works like SRFlow, we tackle this problem in a semi-probabilistic
manner and propose a two-stage pipeline: a divergence stage is used to learn
the distribution of underlying high-resolution outputs in a discrete form, and
a convergence stage is followed to fuse the learned predictions into a final
output. More specifically, we propose a tree-based structure deep network,
where each branch is designed to learn a possible high-resolution prediction.
At the divergence stage, each branch is trained separately to fit ground truth,
and a triple loss is used to enforce the outputs from different branches
divergent. Subsequently, we add a fuse module to combine the multiple
predictions as the outputs from the first stage can be sub-optimal. The fuse
module can be trained to converge w.r.t the final high-resolution image in an
end-to-end manner. We conduct evaluations on several benchmarks, including a
new proposed dataset with 8x upscaling factor. Our experiments demonstrate that
D2C-SR can achieve state-of-the-art performance on PSNR and SSIM, with a
significantly less computational cost.
Related papers
- Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation [58.19676004192321]
Diffusion models (DMs), which enable both image generation from noise and inversion from data, have inspired powerful unpaired image-to-image (I2I) translation algorithms.
We tackle this problem with Schrodinger Bridges (SBs), which are differential equations (SDEs) between distributions with minimal transport cost.
Inspired by this observation, we propose Latent Schrodinger Bridges (LSBs) that approximate the SB ODE via pre-trained Stable Diffusion.
We demonstrate that our algorithm successfully conduct competitive I2I translation in unsupervised setting with only a fraction of cost required by previous DM-
arXiv Detail & Related papers (2024-11-22T11:24:14Z) - Sparse Tensor PCA via Tensor Decomposition for Unsupervised Feature Selection [8.391109286933856]
We develop two Sparse Principal Component Analysis (STPCA) models that utilize the projection directions in the factor matrices to perform unsupervised feature selection.
For both models, we prove the optimal solution of each subproblem falls onto the Hermitian Positive Semidefinite Cone (HPSD)
According to the experimental results, the two proposed methods are suitable for handling different data tensor scenarios and outperform the state-of-the-art UFS methods.
arXiv Detail & Related papers (2024-07-24T04:04:56Z) - Successive Refinement in Large-Scale Computation: Advancing Model
Inference Applications [67.76749044675721]
We introduce solutions for layered-resolution computation.
These solutions allow lower-resolution results to be obtained at an earlier stage than the final result.
arXiv Detail & Related papers (2024-02-11T15:36:33Z) - End-to-end Alternating Optimization for Real-World Blind Super
Resolution [43.95832398891317]
Blind Super-Resolution (SR) usually involves two sub-problems.
estimating the degradation of the given low-resolution (LR) image and super-resolving the LR image to its high-resolution (HR) counterpart.
We propose an alternating optimization algorithm, which can estimate the degradation and restore the SR image in a single model.
arXiv Detail & Related papers (2023-08-17T06:55:09Z) - Dual-Diffusion: Dual Conditional Denoising Diffusion Probabilistic
Models for Blind Super-Resolution Reconstruction in RSIs [6.2678394285548755]
We propose a novel blind SR framework based on conditional denoising diffusion probabilistic models (DDPM)
In our work, we introduce conditional denoising diffusion probabilistic models (DDPM) from two aspects: kernel estimation progress and re-construction progress.
We construct a DDPM-based reconstructor to learning the mapping from the LR images to HR images.
arXiv Detail & Related papers (2023-05-20T11:18:38Z) - Learning To Dive In Branch And Bound [95.13209326119153]
We propose L2Dive to learn specific diving structurals with graph neural networks.
We train generative models to predict variable assignments and leverage the duality of linear programs to make diving decisions.
arXiv Detail & Related papers (2023-01-24T12:01:45Z) - Scaling ResNets in the Large-depth Regime [11.374578778690623]
Deep ResNets are recognized for achieving state-of-the-art results in machine learning tasks.
Deep ResNets rely on a training procedure that needs to be carefully crafted to avoid vanishing or exploding gradients.
No consensus has been reached on how to mitigate this issue, although a widely discussed strategy consists in scaling the output of each layer by a factor $alpha_L$.
arXiv Detail & Related papers (2022-06-14T15:49:10Z) - Combining Deep Learning and Optimization for Security-Constrained
Optimal Power Flow [94.24763814458686]
Security-constrained optimal power flow (SCOPF) is fundamental in power systems.
Modeling of APR within the SCOPF problem results in complex large-scale mixed-integer programs.
This paper proposes a novel approach that combines deep learning and robust optimization techniques.
arXiv Detail & Related papers (2020-07-14T12:38:21Z) - SRFlow: Learning the Super-Resolution Space with Normalizing Flow [176.07982398988747]
Super-resolution is an ill-posed problem, since it allows for multiple predictions for a given low-resolution image.
We propose SRFlow: a normalizing flow based super-resolution method capable of learning the conditional distribution of the output.
Our model is trained in a principled manner using a single loss, namely the negative log-likelihood.
arXiv Detail & Related papers (2020-06-25T06:34:04Z) - Simple and Effective Prevention of Mode Collapse in Deep One-Class
Classification [93.2334223970488]
We propose two regularizers to prevent hypersphere collapse in deep SVDD.
The first regularizer is based on injecting random noise via the standard cross-entropy loss.
The second regularizer penalizes the minibatch variance when it becomes too small.
arXiv Detail & Related papers (2020-01-24T03:44:47Z)
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.