BADiff: Bandwidth Adaptive Diffusion Model

• URL: http://arxiv.org/abs/2510.21366v1
• Date: Fri, 24 Oct 2025 11:50:03 GMT
• Title: BADiff: Bandwidth Adaptive Diffusion Model
• Authors: Xi Zhang, Hanwei Zhu, Yan Zhong, Jiamang Wang, Weisi Lin,
• Abstract summary: Traditional diffusion models produce high-fidelity images by performing a fixed number of denoising steps, regardless of downstream transmission limitations.<n>In practical cloud-to-device scenarios, limited bandwidth often necessitates heavy compression, leading to loss of fine textures and wasted computation.<n>We introduce a joint end-to-end training strategy where the diffusion model is conditioned on a target quality level derived from the available bandwidth.
• Score: 55.10134744772338
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we propose a novel framework to enable diffusion models to adapt their generation quality based on real-time network bandwidth constraints. Traditional diffusion models produce high-fidelity images by performing a fixed number of denoising steps, regardless of downstream transmission limitations. However, in practical cloud-to-device scenarios, limited bandwidth often necessitates heavy compression, leading to loss of fine textures and wasted computation. To address this, we introduce a joint end-to-end training strategy where the diffusion model is conditioned on a target quality level derived from the available bandwidth. During training, the model learns to adaptively modulate the denoising process, enabling early-stop sampling that maintains perceptual quality appropriate to the target transmission condition. Our method requires minimal architectural changes and leverages a lightweight quality embedding to guide the denoising trajectory. Experimental results demonstrate that our approach significantly improves the visual fidelity of bandwidth-adapted generations compared to naive early-stopping, offering a promising solution for efficient image delivery in bandwidth-constrained environments. Code is available at: https://github.com/xzhang9308/BADiff.

Related papers

• FOCUS: Frequency-Optimized Conditioning of DiffUSion Models for mitigating catastrophic forgetting during Test-Time Adaptation [35.2621713113709]
  Test-time adaptation enables models to adapt to evolving domains.<n>Adapting to domain shifts can induce forgetting of task-relevant knowledge.<n>We propose FOCUS, a novel frequency-based conditioning approach within a diffusion-driven input-adaptation framework.
  arXiv  Detail & Related papers  (2025-08-20T05:44:29Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• Semantic-Aware Adaptive Video Streaming Using Latent Diffusion Models for Wireless Networks [12.180483357502293]
  This paper proposes a novel framework for real-time adaptivebitrate video streaming by integrating Latent Diffusion Models (LDMs) within the FF techniques.<n>The proposed approach leverages LDMs to compress I-frames into a latent space, offering significant storage and semantic transmission savings.<n>This work opens new possibilities for scalable real-time video streaming in 5G and future post-5G networks.
  arXiv  Detail & Related papers  (2025-02-08T21:14:28Z)
• Fast constrained sampling in pre-trained diffusion models [80.99262780028015]
  We propose an algorithm that enables fast, high-quality generation under arbitrary constraints.<n>Our approach produces results that rival or surpass the state-of-the-art training-free inference methods.
  arXiv  Detail & Related papers  (2024-10-24T14:52:38Z)
• Diffusion-Driven Semantic Communication for Generative Models with Bandwidth Constraints [66.63250537475973]
  This paper introduces a diffusion-driven semantic communication framework with advanced VAE-based compression for bandwidth-constrained generative model.<n>Our experimental results demonstrate significant improvements in pixel-level metrics like peak signal to noise ratio (PSNR) and semantic metrics like learned perceptual image patch similarity (LPIPS)
  arXiv  Detail & Related papers  (2024-07-26T02:34:25Z)
• 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)
• Exploiting Diffusion Prior for Real-World Image Super-Resolution [75.5898357277047]
  We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution. By employing our time-aware encoder, we can achieve promising restoration results without altering the pre-trained synthesis model.
  arXiv  Detail & Related papers  (2023-05-11T17:55:25Z)

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.