Cross-Resolution Diffusion Models via Network Pruning

• URL: http://arxiv.org/abs/2604.05524v1
• Date: Tue, 07 Apr 2026 07:23:58 GMT
• Title: Cross-Resolution Diffusion Models via Network Pruning
• Abstract summary: CR-Diff is a novel method that improves the cross-resolution visual consistency by pruning some parameters of the diffusion model.<n>It first performs block-wise pruning to selectively eliminate adverse weights.<n>Then, a pruned output amplification is conducted to further purify the predictions.
• Score: 6.220538867840117
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models have demonstrated impressive image synthesis performance, yet many UNet-based models are trained at certain fixed resolutions. Their quality tends to degrade when generating images at out-of-training resolutions. We trace this issue to resolution-dependent parameter behaviors, where weights that function well at the default resolution can become adverse when spatial scales shift, weakening semantic alignment and causing structural instability in the UNet architecture. Based on this analysis, this paper introduces CR-Diff, a novel method that improves the cross-resolution visual consistency by pruning some parameters of the diffusion model. Specifically, CR-Diff has two stages. It first performs block-wise pruning to selectively eliminate adverse weights. Then, a pruned output amplification is conducted to further purify the pruned predictions. Empirically, extensive experiments suggest that CR-Diff can improve perceptual fidelity and semantic coherence across various diffusion backbones and unseen resolutions, while largely preserving the performance at default resolutions. Additionally, CR-Diff supports prompt-specific refinement, enabling quality enhancement on demand.

Related papers

• Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution [69.17533212524447]
  We propose a Difficulty-aware Dynamic Routing ( DDR) strategy that overcomes the rigid, one-size-fits-all processing paradigm.<n>Specifically, we design a difficulty estimator to predict the restoration cost of each input image, enabling automatic assignment to a network of appropriate capacity.<n>Extensive experiments have demonstrated the superior efficiency and effectiveness of the proposed model compared to recent state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-07-17T07:49:05Z)
• ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models [52.648413887350195]
  We propose Stage-Aware RoPE Remapping to suppress global repetition, local repetition, and detail degradation.<n>We also propose Entropy-Driven Adaptive Attention, which quantifies dispersion via a resolution-invariant normalized entropy.<n>Our method consistently outperforms prior resolution-extrapolation methods in both structural coherence and fine-detail fidelity.
  arXiv  Detail & Related papers  (2026-05-11T06:14:38Z)
• InfScene-SR: Spatially Continuous Inference for Arbitrary-Size Image Super-Resolution [3.6762434952581713]
  InfScene-SR is a framework enabling spatially continuous super-resolution for large, arbitrary scenes.<n>We adapt the iterative refinement process of diffusion models with a novel guided and variance-corrected fusion mechanism.
  arXiv  Detail & Related papers  (2026-02-23T11:34:59Z)
• Looking Alike From Far to Near: Enhancing Cross-Resolution Re-Identification via Feature Vector Panning [14.89776496894534]
  Cross-Resolution ReID (CR-ReID) methods rely on super-resolution (SR) or joint learning for feature compensation.<n>Inspired by semantic directions in the word embedding space, we empirically discover that semantic directions implying resolution differences also emerge in the feature space of ReID.<n>We propose a lightweight and effective Vector Panning Feature Alignment (VPFA) framework, which conducts CR-ReID from a novel perspective.
  arXiv  Detail & Related papers  (2025-10-01T14:15:39Z)
• Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution [9.322053509028832]
  We present CasArbi, a self-cascaded diffusion framework for arbitrary-scale image super-resolution.<n>Our novel coordinate-guided residual diffusion model allows for the learning of continuous image representations.<n>Our experiments demonstrate that our CasArbi outperforms prior arts in both perceptual and distortion performance metrics.
  arXiv  Detail & Related papers  (2025-06-09T14:43:21Z)
• BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution [19.568467335629094]
  We introduce the Bayesian Uncertainty Guided Diffusion Probabilistic Model (BUFF)<n>BUFF distinguishes itself by incorporating a Bayesian network to generate high-resolution uncertainty masks.<n>It significantly mitigates artifacts and blurring in areas characterized by complex textures and fine details.
  arXiv  Detail & Related papers  (2025-04-04T14:43:45Z)
• 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)
• DeltaDiff: Reality-Driven Diffusion with AnchorResiduals for Faithful SR [10.790771977682763]
  We propose DeltaDiff, a novel frame.work that constrains the difusion process.<n>Our method surpasses state-of-the-art models and generates re-sults with better fidelity.<n>This work establishes a new low-rank constrained par-adigm for applying diffusion models to image reconstruction tasks.
  arXiv  Detail & Related papers  (2025-02-18T06:07:14Z)
• FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion [63.609399000712905]
  Inference at a scaled resolution leads to repetitive patterns and structural distortions.<n>We propose two simple modules that combine to solve these issues.<n>Our method, coined Fam diffusion, can seamlessly integrate into any latent diffusion model and requires no additional training.
  arXiv  Detail & Related papers  (2024-11-27T17:51:44Z)
• 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)
• Implicit Diffusion Models for Continuous Super-Resolution [65.45848137914592]
  This paper introduces an Implicit Diffusion Model (IDM) for high-fidelity continuous image super-resolution. IDM integrates an implicit neural representation and a denoising diffusion model in a unified end-to-end framework. The scaling factor regulates the resolution and accordingly modulates the proportion of the LR information and generated features in the final output.
  arXiv  Detail & Related papers  (2023-03-29T07:02:20Z)
• Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification [49.57112924976762]
  Cross-resolution person re-identification problem aims to match low-resolution (LR) query identity images against high resolution (HR) gallery images. It is a challenging and practical problem since the query images often suffer from resolution degradation due to the different capturing conditions from real-world cameras. This paper explores an alternative SR-free paradigm to directly compare HR and LR images via a dynamic metric, which is adaptive to the resolution of a query image.
  arXiv  Detail & Related papers  (2022-07-09T03:49:51Z)

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.