NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation

• URL: http://arxiv.org/abs/2510.02307v1
• Date: Thu, 02 Oct 2025 17:59:43 GMT
• Title: NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation
• Authors: Ruozhen He, Moayed Haji-Ali, Ziyan Yang, Vicente Ordonez,
• Abstract summary: Noise schedulers have unequal effects across resolutions.<n>NoiseShift recalibrates the noise level of the denoiser conditioned on resolution size.<n>On LAION-COCO, NoiseShift improves SD3.5 by 15.89%, SD3 by 8.56%, and Flux-Dev by 2.44% in FID on average.
• Score: 16.655610485222997
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Text-to-image diffusion models trained on a fixed set of resolutions often fail to generalize, even when asked to generate images at lower resolutions than those seen during training. High-resolution text-to-image generators are currently unable to easily offer an out-of-the-box budget-efficient alternative to their users who might not need high-resolution images. We identify a key technical insight in diffusion models that when addressed can help tackle this limitation: Noise schedulers have unequal perceptual effects across resolutions. The same level of noise removes disproportionately more signal from lower-resolution images than from high-resolution images, leading to a train-test mismatch. We propose NoiseShift, a training-free method that recalibrates the noise level of the denoiser conditioned on resolution size. NoiseShift requires no changes to model architecture or sampling schedule and is compatible with existing models. When applied to Stable Diffusion 3, Stable Diffusion 3.5, and Flux-Dev, quality at low resolutions is significantly improved. On LAION-COCO, NoiseShift improves SD3.5 by 15.89%, SD3 by 8.56%, and Flux-Dev by 2.44% in FID on average. On CelebA, NoiseShift improves SD3.5 by 10.36%, SD3 by 5.19%, and Flux-Dev by 3.02% in FID on average. These results demonstrate the effectiveness of NoiseShift in mitigating resolution-dependent artifacts and enhancing the quality of low-resolution image generation.

Related papers

• Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance [54.88271057438763]
  Noise Awareness Guidance (NAG) is a correction method that explicitly steers sampling trajectories to remain consistent with the pre-defined noise schedule.<n>NAG consistently mitigates noise shift and substantially improves the generation quality of mainstream diffusion models.
  arXiv  Detail & Related papers  (2025-10-14T13:31:34Z)
• Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers [9.875073051988057]
  Region-Adaptive Latent Upsampling (RALU) is a training-free framework that accelerates inference along spatial dimension.<n>RALU performs mixed-resolution sampling across three stages: 1) low-resolution denoising latent diffusion to efficiently capture global semantic structure, 2) region-adaptive upsampling on specific regions prone to artifacts at full-resolution, and 3) all latent upsampling at full-resolution for detail refinement.<n>Our method significantly reduces computation while preserving image quality by achieving up to 7.0$times$ speed-up on FLUX and 3.0$times$ on Stable Diffusion 3 with minimal degradation.
  arXiv  Detail & Related papers  (2025-07-11T09:07:43Z)
• ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting [70.83632337581034]
  Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed. We propose a novel and efficient diffusion model for SR that significantly reduces the number of diffusion steps. Our method constructs a Markov chain that transfers between the high-resolution image and the low-resolution image by shifting the residual.
  arXiv  Detail & Related papers  (2023-07-23T15:10:02Z)
• 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)
• On the Importance of Noise Scheduling for Diffusion Models [8.360383061862844]
  We study the effect of noise scheduling strategies for denoising diffusion generative models. This simple recipe yields state-of-the-art pixel-based diffusion models for high-resolution images on ImageNet.
  arXiv  Detail & Related papers  (2023-01-26T07:37:22Z)
• Rethinking Noise Synthesis and Modeling in Raw Denoising [75.55136662685341]
  We introduce a new perspective to synthesize noise by directly sampling from the sensor's real noise. It inherently generates accurate raw image noise for different camera sensors.
  arXiv  Detail & Related papers  (2021-10-10T10:45:24Z)
• Noise Conditional Flow Model for Learning the Super-Resolution Space [8.130080378039601]
  Noise Conditional flow model for Super-Resolution, NCSR, increases the visual quality and diversity of images. We show that NCSR outperforms baseline in diversity and visual quality and achieves better visual quality than traditional GAN-based models.
  arXiv  Detail & Related papers  (2021-06-06T07:43:52Z)
• Image Super-Resolution via Iterative Refinement [53.57766722279425]
  SR3 is an approach to image Super-Resolution via Repeated Refinement. It adapts probabilistic denoising diffusion models to conditional image generation. It exhibits strong performance on super-resolution tasks at different magnification factors.
  arXiv  Detail & Related papers  (2021-04-15T17:50:42Z)
• Designing a Practical Degradation Model for Deep Blind Image Super-Resolution [134.9023380383406]
  Single image super-resolution (SISR) methods would not perform well if the assumed degradation model deviates from those in real images. This paper proposes to design a more complex but practical degradation model that consists of randomly shuffled blur, downsampling and noise degradations.
  arXiv  Detail & Related papers  (2021-03-25T17:40:53Z)

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.