D$^2$iT: Dynamic Diffusion Transformer for Accurate Image Generation

• URL: http://arxiv.org/abs/2504.09454v1
• Date: Sun, 13 Apr 2025 06:33:28 GMT
• Title: D$^2$iT: Dynamic Diffusion Transformer for Accurate Image Generation
• Authors: Weinan Jia, Mengqi Huang, Nan Chen, Lei Zhang, Zhendong Mao,
• Abstract summary: Large compression leads to limited local realism, while small compression increases computational complexity and compromises global consistency.<n>We propose dynamically compressing different image regions by recognizing the importance of different regions.<n>We introduce a novel two-stage framework designed to enhance the effectiveness and efficiency of image generation.
• Score: 26.013437773962107
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models are widely recognized for their ability to generate high-fidelity images. Despite the excellent performance and scalability of the Diffusion Transformer (DiT) architecture, it applies fixed compression across different image regions during the diffusion process, disregarding the naturally varying information densities present in these regions. However, large compression leads to limited local realism, while small compression increases computational complexity and compromises global consistency, ultimately impacting the quality of generated images. To address these limitations, we propose dynamically compressing different image regions by recognizing the importance of different regions, and introduce a novel two-stage framework designed to enhance the effectiveness and efficiency of image generation: (1) Dynamic VAE (DVAE) at first stage employs a hierarchical encoder to encode different image regions at different downsampling rates, tailored to their specific information densities, thereby providing more accurate and natural latent codes for the diffusion process. (2) Dynamic Diffusion Transformer (D$^2$iT) at second stage generates images by predicting multi-grained noise, consisting of coarse-grained (less latent code in smooth regions) and fine-grained (more latent codes in detailed regions), through an novel combination of the Dynamic Grain Transformer and the Dynamic Content Transformer. The strategy of combining rough prediction of noise with detailed regions correction achieves a unification of global consistency and local realism. Comprehensive experiments on various generation tasks validate the effectiveness of our approach. Code will be released at https://github.com/jiawn-creator/Dynamic-DiT.

Related papers

• Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression [90.59962443790593]
  In this paper, we present a variable-rate image compression model based on invertible transform to overcome limitations.<n> Specifically, we design a lightweight multi-scale invertible neural network, which maps the input image into multi-scale latent representations.<n> Experimental results demonstrate that the proposed method achieves state-of-the-art performance compared to existing variable-rate methods.
  arXiv  Detail & Related papers  (2025-03-27T09:08:39Z)
• Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers [55.87192133758051]
  Diffusion Transformers (DiTs) have achieved state-of-the-art (SOTA) image generation quality but suffer from high latency and memory inefficiency.<n>We propose DiffCR, a dynamic DiT inference framework with differentiable compression ratios.
  arXiv  Detail & Related papers  (2024-12-22T02:04:17Z)
• Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization [73.52943587514386]
  Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm. We propose a novel two-stage framework: (1) Dynamic-Quantization VAE (DQ-VAE) which encodes image regions into variable-length codes based their information densities for accurate representation.
  arXiv  Detail & Related papers  (2023-05-19T14:56:05Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• Diverse Image Inpainting with Bidirectional and Autoregressive Transformers [55.21000775547243]
  We propose BAT-Fill, an image inpainting framework with a novel bidirectional autoregressive transformer (BAT) BAT-Fill inherits the merits of transformers and CNNs in a two-stage manner, which allows to generate high-resolution contents without being constrained by the quadratic complexity of attention in transformers.
  arXiv  Detail & Related papers  (2021-04-26T03:52:27Z)
• Efficient texture-aware multi-GAN for image inpainting [5.33024001730262]
  Recent GAN-based (Generative adversarial networks) inpainting methods show remarkable improvements. We propose a multi-GAN architecture improving both the performance and rendering efficiency.
  arXiv  Detail & Related papers  (2020-09-30T14:58:03Z)
• Generalized Octave Convolutions for Learned Multi-Frequency Image Compression [20.504561050200365]
  We propose the first learned multi-frequency image compression and entropy coding approach. It is based on the recently developed octave convolutions to factorize the latents into high and low frequency (resolution) components. We show that the proposed generalized octave convolution can improve the performance of other auto-encoder-based computer vision tasks.
  arXiv  Detail & Related papers  (2020-02-24T01:35:29Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)

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.