Detail Continuation over a Trustworthy Coarse Scale for Autoregressive Super-Resolution

• URL: http://arxiv.org/abs/2608.01823v2
• Date: Tue, 04 Aug 2026 02:39:04 GMT
• Title: Detail Continuation over a Trustworthy Coarse Scale for Autoregressive Super-Resolution
• Abstract summary: Hallucination remains a persistent challenge in generative super-resolution.<n> division between preserving reliable coarse-scale information and restoring more uncertain fine details is often handled implicitly.<n>We propose textbfK2N, which reformulates VAR-based SR from full-path generation into a $k$-to-$N$ detail continuation process.
• Score: 11.303661953283894
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hallucination remains a persistent challenge in generative super-resolution (GSR), where reconstructed results may contain visually plausible yet weakly supported content, structural deviations, or unnatural textures with respect to the low-resolution (LR) input. Existing GSR methods have extensively explored the trade-off between perceptual realism and reconstruction fidelity, but the division between preserving reliable coarse-scale information and restoring more uncertain fine details is often handled implicitly within the overall restoration process. Visual autoregressive (VAR) modeling provides a natural opportunity to revisit this issue, as its coarse-to-fine next-scale prediction offers an explicit scale-wise generation interface. However, existing VAR-based SR methods still inherit the original full 1-to-$N$ autoregressive generation path, even though, for super-resolution, coarse-scale information in LR is often relatively more reliable, while long autoregressive chains may accumulate prediction errors. Motivated by these observations, we propose \textbf{K2N}, which reformulates VAR-based SR from full-path generation into a $k$-to-$N$ detail continuation process. Specifically, early coarse-scale states are established directly from LR, while only the remaining finer scales are restored autoregressively. Experimental results show that K2N remains competitive with the VARSR baseline on standard SR metrics, while exhibiting clearer advantages on hallucination-focused evaluation. These findings suggest that explicitly rethinking the generation path in a scale-wise manner can be a promising direction for improving the reliability of generative super-resolution. Our code will be released soon at https://github.com/BRL-SYSU/K2NSR.

Related papers

• MeanSR: Restoration Trajectory Learning for One-Step Perceptual Super-Resolution [50.60539317126614]
  MeanSR learns an LR-conditioned average velocity field to directly capture the finite-time transition from noisy inputs to plausible HR outputs.<n>Experiments show that MeanSR outperforms CTMSR on CLIPIQA, MUSIQ, and MANIQA while substantially reducing FLOPs and inference latency.
  arXiv  Detail & Related papers  (2026-08-10T10:33:18Z)
• When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-Resolution [47.89708788628452]
  We propose a pixel-grounded super-resolution (PGSR) framework that preserves LR-observed pixel evidence before VAE compression and reuses it throughout restoration.<n>Experiments demonstrate that PGSR improves the realism--fidelity trade-off and produces more faithful, visually convincing results than existing latent generative SR approaches.
  arXiv  Detail & Related papers  (2026-08-10T05:24:39Z)
• RefGC-SR$^2$: Reference-guided Generated Content Super-Resolution and Refinement [12.971780703663754]
  We introduce a new task: reference-guided generated content super-resolution-refinement (RefGC-SR$2$)<n>The original HRRI is reused at the post-processing stage to recover lost details, refine generative artifacts, and upscale the output simultaneously.<n>We construct the first real-world triplet data generation pipeline for this RefGC-SR$2$ task, training a diptych-conditioned generator to synthesize paired low-quality anchors.
  arXiv  Detail & Related papers  (2026-06-13T07:04:36Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction [52.32112533846212]
  MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions.<n>We address this limitation by moving reconstruction to discrete multi-scale latent space and posing it as autoregressive next-acceleration-scale prediction.<n>We show that our approach delivers improved reconstruction performance across diverse sampling patterns under extreme undersampling.
  arXiv  Detail & Related papers  (2026-05-19T04:40:50Z)
• DegBins: Degradation-Driven Binning for Depth Super-Resolution [57.61783461543096]
  DegBins is a novel DSR framework that leverages degradation-driven binning to adaptively enhance residual modeling.<n>DegBins consistently outperforms existing state-of-the-art methods in terms of accuracy, robustness, and generalization.
  arXiv  Detail & Related papers  (2026-05-10T16:17:11Z)
• Allo{SR}$^2$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows [32.29950358173077]
  Real-world image super-resolution (Real-SR) has been revolutionized by leveraging the powerful generative priors of large-scale diffusion and flow-based models.<n>AlloSR$2$ is a novel framework that rectifies one-step SR trajectories via allomorphic generative flows to maintain high-fidelity generative realism.
  arXiv  Detail & Related papers  (2026-04-21T08:44:40Z)
• RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution [26.50828843718706]
  RefReward-SR is a low-resolution (LR) reference-aware reward model for preference-aligned SR.<n>It assesses high-resolution (HR) reconstructions conditioned on LR inputs, treating the LR image as a semantic anchor.<n>Our framework achieves substantially better alignment with human judgments, producing reconstructions that preserve semantic consistency.
  arXiv  Detail & Related papers  (2026-03-25T11:20:51Z)
• FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution [11.03986460753769]
  We propose FiDeSR, a high-fidelity and detail-preserving one-step diffusion super-resolution framework.<n>During training, we introduce a detail-aware weighting strategy that adaptively emphasizes regions where the model exhibits higher prediction errors.<n>During inference, low- and high-frequency adaptive enhancers further refine the reconstruction without requiring model retraining.
  arXiv  Detail & Related papers  (2026-03-03T07:34:49Z)
• Recursive Think-Answer Process for LLMs and VLMs [54.52289112197118]
  We propose an efficient Recursive Think-Answer Process (R-TAP)<n>R-TAP enables models to engage in iterative reasoning cycles and generate more accurate answers.<n>We show that R-TAP-enhanced models consistently outperform conventional single-pass methods.
  arXiv  Detail & Related papers  (2026-03-02T17:20:10Z)
• AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution [16.90182090355781]
  Visual autoregressive models offer stable training, non-iterative inference, and high-fidelity synthesis through next-scale prediction.<n>But their application remains underexplored and faces two critical challenges: locality-biased attention, and residual-only supervision.<n>We propose a globally consistent visual autoregressive framework tailored for image super-resolution.
  arXiv  Detail & Related papers  (2026-02-28T10:39:06Z)

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.