Boosting Flow-based Generative Super-Resolution Models via Learned Prior

• URL: http://arxiv.org/abs/2403.10988v3
• Date: Wed, 29 May 2024 03:12:58 GMT
• Title: Boosting Flow-based Generative Super-Resolution Models via Learned Prior
• Authors: Li-Yuan Tsao, Yi-Chen Lo, Chia-Che Chang, Hao-Wei Chen, Roy Tseng, Chien Feng, Chun-Yi Lee,
• Abstract summary: Flow-based super-resolution (SR) models have demonstrated astonishing capabilities in generating high-quality images. These methods encounter several challenges during image generation, such as grid artifacts, exploding inverses, and suboptimal results due to a fixed sampling temperature. This work introduces a conditional learned prior to the inference phase of a flow-based SR model.
• Score: 8.557017814978334
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Flow-based super-resolution (SR) models have demonstrated astonishing capabilities in generating high-quality images. However, these methods encounter several challenges during image generation, such as grid artifacts, exploding inverses, and suboptimal results due to a fixed sampling temperature. To overcome these issues, this work introduces a conditional learned prior to the inference phase of a flow-based SR model. This prior is a latent code predicted by our proposed latent module conditioned on the low-resolution image, which is then transformed by the flow model into an SR image. Our framework is designed to seamlessly integrate with any contemporary flow-based SR model without modifying its architecture or pre-trained weights. We evaluate the effectiveness of our proposed framework through extensive experiments and ablation analyses. The proposed framework successfully addresses all the inherent issues in flow-based SR models and enhances their performance in various SR scenarios. Our code is available at: https://github.com/liyuantsao/BFSR

Related papers

• Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors [75.24313405671433]
  Diffusion-based image super-resolution (SR) methods have achieved remarkable success by leveraging large pre-trained text-to-image diffusion models as priors. We introduce a novel one-step SR model, which significantly addresses the efficiency issue of diffusion-based SR methods. Unlike existing fine-tuning strategies, we designed a degradation-guided Low-Rank Adaptation (LoRA) module specifically for SR.
  arXiv  Detail & Related papers  (2024-09-25T16:15:21Z)
• Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction [62.955327005837475]
  Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images. We present an efficient test-time adaptation framework for SR, named SRTTA, which is able to quickly adapt SR models to test domains with different/unknown degradation types.
  arXiv  Detail & Related papers  (2023-10-29T13:58:57Z)
• ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution [84.73658185158222]
  We propose a diffusion model-based super-resolution method called ACDMSR. Our method adapts the standard diffusion model to perform super-resolution through a deterministic iterative denoising process. Our approach generates more visually realistic counterparts for low-resolution images, emphasizing its effectiveness in practical scenarios.
  arXiv  Detail & Related papers  (2023-07-03T06:49:04Z)
• Super-resolution Reconstruction of Single Image for Latent features [8.857209365343646]
  Single-image super-resolution (SISR) typically focuses on restoring various degraded low-resolution (LR) images to a single high-resolution (HR) image. It is often challenging for models to simultaneously maintain high quality and rapid sampling while preserving diversity in details and texture features. This challenge can lead to issues such as model collapse, lack of rich details and texture features in the reconstructed HR images, and excessive time consumption for model sampling.
  arXiv  Detail & Related papers  (2022-11-16T09:37:07Z)
• Bayesian Image Super-Resolution with Deep Modeling of Image Statistics [18.55701190218365]
  We propose a Bayesian image restoration framework, where natural image statistics are modeled with the combination of smoothness and sparsity priors. We develop a variational Bayesian approach to infer their posteriors, and propose an unsupervised training strategy. Experiments on three image restoration tasks, textiti.e., ideal SISR, realistic SISR, and real-world SISR, demonstrate that our method has superior model generalizability against varying noise levels and degradation kernels.
  arXiv  Detail & Related papers  (2022-03-31T20:52:59Z)
• Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling [139.25215100378284]
  We propose a hierarchical conditional flow (HCFlow) as a unified framework for image SR and image rescaling. HCFlow learns a mapping between HR and LR image pairs by modelling the distribution of the LR image and the rest high-frequency component simultaneously. To further enhance the performance, other losses such as perceptual loss and GAN loss are combined with the commonly used negative log-likelihood loss in training.
  arXiv  Detail & Related papers  (2021-08-11T16:11:01Z)
• 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)
• Normalizing Flows with Multi-Scale Autoregressive Priors [131.895570212956]
  We introduce channel-wise dependencies in their latent space through multi-scale autoregressive priors (mAR) Our mAR prior for models with split coupling flow layers (mAR-SCF) can better capture dependencies in complex multimodal data. We show that mAR-SCF allows for improved image generation quality, with gains in FID and Inception scores compared to state-of-the-art flow-based models.
  arXiv  Detail & Related papers  (2020-04-08T09:07:11Z)

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.