Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration
Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inherent interference among hybrid distortions which compromises the restoration performance. To decompose such interference, we introduce the concept of Disentangled Feature Learning to achieve the feature-level divide-and-conquer of hybrid distortions. Specifically, we propose the feature disentanglement module (FDM) to distribute feature representations of different distortions into different channels by revising gain-control-based normalization. We also propose a feature aggregation module (FAM) with channel-wise attention to adaptively filter out the distortion representations and aggregate useful content information from different channels for the construction of raw image. The effectiveness of the proposed scheme is verified by visualizing the correlation matrix of features and channel responses of different distortions. Extensive experimental results also prove superior performance of our approach compared with the latest HD-IR schemes.
Code (0)
등록된 구현이 없습니다.
Tasks
DisentanglementImage RestorationSimilar Papers 제목 키워드 기반
Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
The latent space of diffusion model mostly still remains unexplored, despite its great success and potential in the field of generative modeling. In fact, the latent space of existing diffusion models are entangled, with…
Representation LearningDualVAE: Controlling Colours of Generated and Real Images
Colour controlled image generation and manipulation are of interest to artists and graphic designers. Vector Quantised Variational AutoEncoders (VQ-VAEs) with autoregressive (AR) prior are able to produce high quality im…
Image GenerationDisentangle Perceptual Learning through Online Contrastive Learning
Pursuing realistic results according to human visual perception is the central concern in the image transformation tasks. Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but th…
Contrastive Learningfeature selectionTripletPrivate-Shared Disentangled Multimodal VAE for Learning of Hybrid Latent Representations
Multi-modal generative models represent an important family of deep models, whose goal is to facilitate representation learning on data with multiple views or modalities. However, current deep multi-modal models focus on…
DisentanglementRepresentation LearningHybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation
Generating high-quality videos that synthesize desired realistic content is a challenging task due to their intricate high-dimensionality and complexity of videos. Several recent diffusion-based methods have shown compar…
Video GenerationVideo Reconstruction