Skip to content
Preprint

GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration

Sep 2026 · 0 citations · 65 references
Computer Science

TL;DR

GraLoD, a plug-and-play framework that treats restoration scale as a spatially varying and stage-dependent continuous variable, is proposed and minimal-sufficient footprint calibration (MSFC) together with structure-aware regularization (SAR) is introduced to encourage restoration-effective and spatially coherent LOD assignments.

Abstract

The spatial support required for image restoration varies across degradation types, image regions, and reconstruction stages. However, most existing methods rely on predefined multi-scale hierarchies and aggregate features through fixed fusion or attention, leaving the representation scale itself largely determined by the network architecture. This limitation becomes more pronounced when a task-specific backbone is extended to heterogeneous degradations in all-in-one restoration. Inspired by level-of-detail (LOD) rendering in computer graphics, we propose GraLoD, a plug-and-play framework that treats restoration scale as a spatially varying and stage-dependent continuous variable. GraLoD reuses the native encoder hierarchy, aligns its multi-scale features into a shared LOD representation space, and predicts a stage-conditioned LOD field at each decoder stage. Each spatial location then continuously queries only two neighboring representation levels, enabling the effective restoration scale to adapt to both local image content and reconstruction progress. To prevent degenerate or arbitrary scale selection, we further introduce minimal-sufficient footprint calibration (MSFC) together with structure-aware regularization (SAR) to encourage restoration-effective and spatially coherent LOD assignments. GraLoD can be directly integrated into existing restoration backbones without redesigning their fundamental feature-processing blocks. Extensive experiments demonstrate consistent improvements in task-specific and all-in-one restoration.

View source

Similar papers

Open access Oct 2026

MDIRNET: Multi-Degradation Image Restoration Network via Deep Unfolding

Real images often exhibit unknown and mixed degradations, making restoration substantially more challenging than single-task image restoration because multiple distortion types interact within the same observation. Consequently, existing methods often rely on prior knowledge of the degradation type or separate task-spe...

T. Nadeem, Arslan Majal, Muhammad Tahir et al. · 0 citations
Preprint Aug 2026

MagnifiQ: Patch-aware Text Guided Progressive Upscaling for High-Resolution Image Restoration

MagnifiQ is introduced, an image restoration framework that progressively upscales and restores images across resolutions, e.g., from 1024x1024 to 4096x4096, and leverages a pre-trained text-to-image diffusion model such as SDXL and adapts it for more scalable high-resolution inference by replacing its original self-at...

M. Reddy, Yashesh Savani, Antoine Mercier et al. · 0 citations
Preprint Sep 2026

BTC3D: Blended Tile Conditioning for Detail-Enhancing Image-to-3D Generation

Recent diffusion-based pipelines have achieved promising progress in image-to-3D synthesis. However, generating high-fidelity details remains challenging, especially when the input image contains rich details. Existing approaches often rely on globally encoded conditioning features, which compress spatial information a...

Jun-Yu Li, Qiu-Yu Chen, Peng-Cheng Wang et al. · 0 citations
Aug 2026

AdaMultiGAN: an adaptive multiscale decoding framework for few-shot image generation

An adaptive multi-scale decoding framework that effectively balances global context with fine-grained detail is proposed that exhibits superior robustness and generalization across diverse domains, effectively alleviating limitations of existing fusion-based approaches.

Yu Luo, Chun-Na Zhao, Ya-Qun Huang · 0 citations
Sep 2026

Retinex-informed efficient visual state space networks for shadow removal

This paper develops a Retinex-guided state space backbone that integrates illumination–reflectance priors into the network in a structured manner, enabling more reliable restoration of shadow regions, and introduces a Shadow Interaction Module within a multi-scale channel attention framework.

Wei-Ju Zhao, Run-Xing Zhao, Shi-Jian Yang · 0 citations
Preprint Aug 2026

PixRestore: Unified Image Restoration via Pixel Diffusion Transformer

PixRestore is presented, a VAE-free pixel-space Diffusion Transformer (DiT) for UIR, where the diffusion backbone is trained entirely from scratch, without relying on T2I pretraining.

Ling-Chen Sun, Rong-Yuan Wu, Xiang-Tao Kong et al. · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.