ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration

• URL: http://arxiv.org/abs/2504.08591v1
• Date: Fri, 11 Apr 2025 14:49:52 GMT
• Title: ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration
• Authors: Yongsheng Yu, Haitian Zheng, Zhifei Zhang, Jianming Zhang, Yuqian Zhou, Connelly Barnes, Yuchen Liu, Wei Xiong, Zhe Lin, Jiebo Luo,
• Abstract summary: We introduce ZipIR, a novel framework that enhances efficiency, scalability, and long-range modeling for high-res image restoration.<n>ZipIR employs a highly compressed latent representation that compresses image 32x, effectively reducing the number of spatial tokens.<n>ZipIR surpasses existing diffusion-based methods, offering unmatched speed and quality in restoring high-resolution images from severely degraded inputs.
• Score: 75.0053551643052
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent progress in generative models has significantly improved image restoration capabilities, particularly through powerful diffusion models that offer remarkable recovery of semantic details and local fidelity. However, deploying these models at ultra-high resolutions faces a critical trade-off between quality and efficiency due to the computational demands of long-range attention mechanisms. To address this, we introduce ZipIR, a novel framework that enhances efficiency, scalability, and long-range modeling for high-res image restoration. ZipIR employs a highly compressed latent representation that compresses image 32x, effectively reducing the number of spatial tokens, and enabling the use of high-capacity models like the Diffusion Transformer (DiT). Toward this goal, we propose a Latent Pyramid VAE (LP-VAE) design that structures the latent space into sub-bands to ease diffusion training. Trained on full images up to 2K resolution, ZipIR surpasses existing diffusion-based methods, offering unmatched speed and quality in restoring high-resolution images from severely degraded inputs.

Related papers

• MambaIC: State Space Models for High-Performance Learned Image Compression [53.991726013454695]
  A high-performance image compression algorithm is crucial for real-time information transmission across numerous fields.<n>Inspired by the effectiveness of state space models (SSMs) in capturing long-range dependencies, we leverage SSMs to address computational inefficiency in existing methods.<n>We propose an enhanced image compression approach through refined context modeling, which we term MambaIC.
  arXiv  Detail & Related papers  (2025-03-16T11:32:34Z)
• Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models [33.519892081718716]
  We propose aligning the latent space with pre-trained vision foundation models when training the visual tokenizers.<n>Our proposed VA-VAE significantly expands the reconstruction-generation frontier of latent diffusion models.<n>We build an enhanced DiT baseline with improved training strategies and architecture designs, termed LightningDiT.
  arXiv  Detail & Related papers  (2025-01-02T18:59:40Z)
• Effective Diffusion Transformer Architecture for Image Super-Resolution [63.254644431016345]
  We design an effective diffusion transformer for image super-resolution (DiT-SR) In practice, DiT-SR leverages an overall U-shaped architecture, and adopts a uniform isotropic design for all the transformer blocks. We analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module.
  arXiv  Detail & Related papers  (2024-09-29T07:14:16Z)
• Timestep-Aware Diffusion Model for Extreme Image Rescaling [47.89362819768323]
  We propose a novel framework called Timestep-Aware Diffusion Model (TADM) for extreme image rescaling.<n>TADM performs rescaling operations in the latent space of a pre-trained autoencoder.<n>It effectively leverages powerful natural image priors learned by a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-08-17T09:51:42Z)
• Diffusion Models Without Attention [110.5623058129782]
  Diffusion State Space Model (DiffuSSM) is an architecture that supplants attention mechanisms with a more scalable state space model backbone. Our focus on FLOP-efficient architectures in diffusion training marks a significant step forward.
  arXiv  Detail & Related papers  (2023-11-30T05:15:35Z)
• Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging [17.511583657111792]
  Snapshot spectral imaging reconstruction aims to reconstruct three-dimensional spatial-spectral images from a single-shot two-dimensional compressed measurement. We introduce a generative model, namely the latent diffusion model (LDM), to generate degradation-free prior to deep unfolding method.
  arXiv  Detail & Related papers  (2023-11-24T04:55:20Z)
• Low-Light Image Enhancement with Wavelet-based Diffusion Models [50.632343822790006]
  Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. We propose a robust and efficient Diffusion-based Low-Light image enhancement approach, dubbed DiffLL.
  arXiv  Detail & Related papers  (2023-06-01T03:08:28Z)
• Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Models [9.245782611878752]
  We enhance the diffusion model in several aspects such as network architecture, noise level, denoising steps, training image size, and perceptual/scheduler scores. We also propose a U-Net based latent diffusion model which performs diffusion in a low-resolution latent space while preserving high-resolution information from the original input for the decoding process. These modifications allow us to apply diffusion models to various image restoration tasks, including real-world shadow removal, HR non-homogeneous dehazing, stereo super-resolution, and bokeh effect transformation.
  arXiv  Detail & Related papers  (2023-04-17T14:06:49Z)

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.