paper-with-me

홈 › Papers

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

2026-09-15 · Hu Gao, Lizhuang Ma, Yulong Chen arxiv

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.

📄 PDF Abstract BibTeX arXiv:2609.16578

Code (0)

등록된 구현이 없습니다.

Tasks

Image Restoration

Similar Papers 제목 키워드 기반

Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent Visibility

2025-05-27 · CVPR 2025 1 · Yidi Li, Jun Xiao, Zhengda Lu, Yiqun Wang 외

This work presents a novel text-to-vector graphics generation approach, Dream3DVG, allowing for arbitrary viewpoint viewing, progressive detail optimization, and view-dependent occlusion awareness. Our approach is a dual…

3DGSSchedulingVector Graphics

BERT4Traj: Transformer Based Trajectory Reconstruction for Sparse Mobility Data

2025-07-03 · Hao Yang, Angela Yao, Christopher Whalen, Gengchen Mai arxiv

Understanding human mobility is essential for applications in public health, transportation, and urban planning. However, mobility data often suffers from sparsity due to limitations in data collection methods, such as i…

CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting

2025-10-11 · Zhigang Cheng, Mingchao Sun, Yu Liu, Zengye Ge 외 arxiv

Level of Detail (LoD) is a fundamental technique in real-time computer graphics for managing the rendering costs of complex scenes while preserving visual fidelity. Traditionally, LoD is implemented using discrete levels…

Re-Thinking Inverse Graphics With Large Language Models

2024-04-23 · Peter Kulits, Haiwen Feng, Weiyang Liu, Victoria Abrevaya 외

Inverse graphics -- the task of inverting an image into physical variables that, when rendered, enable reproduction of the observed scene -- is a fundamental challenge in computer vision and graphics. Successfully disent…

Language ModellingLarge Language ModelSpatial ReasoningWorld Knowledge

SVGformer: Representation Learning for Continuous Vector Graphics Using Transformers

2023-01-01 · CVPR 2023 1 · Defu Cao, Zhaowen Wang, Jose Echevarria, Yan Liu

Advances in representation learning have led to great success in understanding and generating data in various domains. However, in modeling vector graphics data, the pure data-driven approach often yields unsatisfact…

QuantizationRepresentation LearningRetrievalVector Graphics