ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models

• URL: http://arxiv.org/abs/2605.10045v1
• Date: Mon, 11 May 2026 06:14:38 GMT
• Title: ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models
• Abstract summary: 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.
• Score: 52.648413887350195
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual Autoregressive (VAR) models have emerged as a strong alternative to diffusion for image synthesis, yet their fixed training resolution prevents direct generation at higher resolutions. Naively transferring training-free extrapolation methods from LLMs or diffusion models to VAR yields three characteristic failure modes: global repetition, local repetition, and detail degradation. We trace them to a unified band-stage mismatch: VAR generates images in a coarse-to-fine, scale-wise process where each stage is driven by a distinct dominant RoPE frequency band, and each failure mode emerges when the dominant band of a particular stage is disrupted. Building on this insight, we propose Stage-Aware RoPE Remapping, a training-free strategy that assigns each frequency band a stage-specific remapping rule, jointly suppressing all three failure modes. We further observe that attention becomes systematically dispersed as the image resolution increases. Existing methods typically depend on predefined attention scaling factors, which are neither adaptive to the target resolution nor capable of faithfully capturing the actual extent of attention dispersion. We therefore propose Entropy-Driven Adaptive Attention Calibration, which quantifies dispersion via a resolution-invariant normalized entropy and yields a closed-form per-head scaling factor that realigns the extrapolated-resolution attention entropy with its training-resolution counterpart. Extensive experiments show that our method consistently outperforms prior resolution-extrapolation methods in both structural coherence and fine-detail fidelity. Our code is available at https://github.com/feihongyan1/ExtraVAR.

Related papers

• 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)
• Robust Posterior Diffusion-based Sampling via Adaptive Guidance Scale [39.27744518020771]
  We propose an adaptive likelihood step-size strategy to guide the diffusion process for inverse-problem formulations.<n>The resulting approach, Adaptive Posterior diffusion Sampling (AdaPS), is hyper-free and improves reconstruction quality across diverse imaging tasks.
  arXiv  Detail & Related papers  (2025-11-23T14:37:59Z)
• Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance [52.705112811734566]
  A novel diffusion-based framework is introduced for solving inverse problems using a piecewise guidance scheme.<n>The proposed method is problem-agnostic and readily adaptable to a variety of inverse problems.<n>The framework achieves a reduction in inference time of (25%) for inpainting with both random and center masks, and (23%) and (24%) for (4times) and (8times) super-resolution tasks.
  arXiv  Detail & Related papers  (2025-07-22T19:35:14Z)
• 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)
• Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual [47.141811103506036]
  We propose a novel zero-shot image restoration scheme dubbed Reconciling Model in Dual (RDMD)<n>RDMD uses only a bftextsingle pre-trained diffusion model to construct texttwo regularizers.<n>Our proposed method could achieve superior results compared to existing approaches on both the FFHQ and ImageNet datasets.
  arXiv  Detail & Related papers  (2025-03-03T08:25:22Z)
• 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)
• Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
  Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-22T12:18:20Z)
• 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)
• A Variational Perspective on Solving Inverse Problems with Diffusion Models [101.831766524264]
  Inverse tasks can be formulated as inferring a posterior distribution over data. This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable. We propose a variational approach that by design seeks to approximate the true posterior distribution.
  arXiv  Detail & Related papers  (2023-05-07T23:00:47Z)

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.