Imagen de Portada

Decouple to Reconstruct: High Quality UHD Restoration via Active Feature Disentanglement and Reversible Fusion

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Yidi, Li, Dong, Ma, Yuxin, Huang, Jie, Zhang, Wenlong, Fu, Xueyang, Zha, Zheng-jun
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement
por: Liu, Yidi, et al.
Publicado: (2025)

FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution
por: Liu, Yidi, et al.
Publicado: (2025)

FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining
por: Li, Dong, et al.
Publicado: (2024)

IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow
por: Fan, Zihao, et al.
Publicado: (2026)

Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration
por: Lu, Xin, et al.
Publicado: (2025)

Correlation Matching Transformation Transformers for UHD Image Restoration
por: Wang, Cong, et al.
Publicado: (2024)

TSFormer: A Robust Framework for Efficient UHD Image Restoration
por: Su, Xin, et al.
Publicado: (2024)

Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration
por: Wu, Chen, et al.
Publicado: (2024)

From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark
por: Zhao, Chen, et al.
Publicado: (2026)

Iterative Inference-time Scaling with Adaptive Frequency Steering for Image Super-Resolution
por: Zhang, Hexin, et al.
Publicado: (2025)

Bird-SR: Bidirectional Reward-Guided Diffusion for Real-World Image Super-Resolution
por: Fan, Zihao, et al.
Publicado: (2026)

UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions
por: Xue, Zhucun, et al.
Publicado: (2025)

EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction
por: Ge, Chengjie, et al.
Publicado: (2025)

UHD-GPGNet: UHD Video Denoising via Gaussian-Process-Guided Local Spatio-Temporal Modeling
por: He, Weiyuan, et al.
Publicado: (2026)

Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancement
por: Wang, Cong, et al.
Publicado: (2026)

AIM 2024 Challenge on UHD Blind Photo Quality Assessment
por: Hosu, Vlad, et al.
Publicado: (2024)

Towards Better De-raining Generalization via Rainy Characteristics Memorization and Replay
por: Wang, Kunyu, et al.
Publicado: (2025)

Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restoration
por: Peng, Long, et al.
Publicado: (2025)

UHD Low-Light Image Enhancement via Real-Time Enhancement Methods with Clifford Information Fusion
por: Wang, Xiaohan, et al.
Publicado: (2026)

DATA: Domain-And-Time Alignment for High-Quality Feature Fusion in Collaborative Perception
por: Tian, Chengchang, et al.
Publicado: (2025)

SCott: Accelerating Diffusion Models with Stochastic Consistency Distillation
por: Liu, Hongjian, et al.
Publicado: (2024)

StyleDecoupler: Generalizable Artistic Style Disentanglement
por: Jia, Zexi, et al.
Publicado: (2026)

Assessing UHD Image Quality from Aesthetics, Distortions, and Saliency
por: Sun, Wei, et al.
Publicado: (2024)

RetinexDualV2: Physically-Grounded Dual Retinex for Generalized UHD Image Restoration
por: Kishawy, Mohab, et al.
Publicado: (2026)

Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset
por: Xu, Senyan, et al.
Publicado: (2026)

UHD Image Deblurring via Autoregressive Flow with Ill-conditioned Constraints
por: Xin, Yucheng, et al.
Publicado: (2026)

Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning
por: Wang, Kunyu, et al.
Publicado: (2025)

HDMoE: A Hierarchical Decoupling-Fusion Mixture-of-Experts Framework for Multimodal Cancer Survival Prediction
por: Wang, Huayi, et al.
Publicado: (2026)

DDFusion:Degradation-Decoupled Fusion Framework for Robust Infrared and Visible Images Fusion
por: Zhang, Tianpei, et al.
Publicado: (2025)

Single Image to High-Quality 3D Object via Latent Features
por: Dong, Huanning, et al.
Publicado: (2025)

One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control
por: Mi, Zhenxing, et al.
Publicado: (2025)

RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions
por: Wu, Anran, et al.
Publicado: (2025)

PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration
por: Zhang, Dingxin, et al.
Publicado: (2023)

DemosaicFormer: Coarse-to-Fine Demosaicing Network for HybridEVS Camera
por: Xu, Senyan, et al.
Publicado: (2024)

Disentangle Object and Non-object Infrared Features via Language Guidance
por: Liu, Fan, et al.
Publicado: (2026)

UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache
por: Wang, Pu, et al.
Publicado: (2025)

UHD-IQA Benchmark Database: Pushing the Boundaries of Blind Photo Quality Assessment
por: Hosu, Vlad, et al.
Publicado: (2024)

LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer
por: Zhang, Yipeng, et al.
Publicado: (2024)

Doctoral Thesis: Geometric Deep Learning For Camera Pose Prediction, Registration, Depth Estimation, and 3D Reconstruction
por: Kang, Xueyang
Publicado: (2025)

ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration
por: Ni, Chaojun, et al.
Publicado: (2024)