Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917038515027968 |
|---|---|
| author | Liu, Yidi Fu, Xueyang Huang, Jie Xiao, Jie Li, Dong Zhang, Wenlong Bai, Lei Zha, Zheng-Jun |
| author_facet | Liu, Yidi Fu, Xueyang Huang, Jie Xiao, Jie Li, Dong Zhang, Wenlong Bai, Lei Zha, Zheng-Jun |
| contents | Ultra-High Definition (UHD) image restoration faces a trade-off between computational efficiency and high-frequency detail retention. While Variational Autoencoders (VAEs) improve efficiency via latent-space processing, their Gaussian constraint often discards degradation-specific high-frequency information, hurting reconstruction fidelity. To overcome this, we propose Latent Harmony, a two-stage framework that redefines VAEs for UHD restoration by jointly regularizing the latent space and enforcing high-frequency-aware reconstruction.In Stage One, we introduce LH-VAE, which enhances semantic robustness through visual semantic constraints and progressive degradation perturbations, while latent equivariance strengthens high-frequency reconstruction.Stage Two jointly trains this refined VAE with a restoration model using High-Frequency Low-Rank Adaptation (HF-LoRA): an encoder LoRA guided by a fidelity-oriented high-frequency alignment loss to recover authentic details, and a decoder LoRA driven by a perception-oriented loss to synthesize realistic textures. Both LoRA modules are trained via alternating optimization with selective gradient propagation to preserve the pretrained latent structure.At inference, a tunable parameter α enables flexible fidelity-perception trade-offs.Experiments show Latent Harmony achieves state-of-the-art performance across UHD and standard-resolution tasks, effectively balancing efficiency, perceptual quality, and reconstruction accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07961 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement Liu, Yidi Fu, Xueyang Huang, Jie Xiao, Jie Li, Dong Zhang, Wenlong Bai, Lei Zha, Zheng-Jun Computer Vision and Pattern Recognition Ultra-High Definition (UHD) image restoration faces a trade-off between computational efficiency and high-frequency detail retention. While Variational Autoencoders (VAEs) improve efficiency via latent-space processing, their Gaussian constraint often discards degradation-specific high-frequency information, hurting reconstruction fidelity. To overcome this, we propose Latent Harmony, a two-stage framework that redefines VAEs for UHD restoration by jointly regularizing the latent space and enforcing high-frequency-aware reconstruction.In Stage One, we introduce LH-VAE, which enhances semantic robustness through visual semantic constraints and progressive degradation perturbations, while latent equivariance strengthens high-frequency reconstruction.Stage Two jointly trains this refined VAE with a restoration model using High-Frequency Low-Rank Adaptation (HF-LoRA): an encoder LoRA guided by a fidelity-oriented high-frequency alignment loss to recover authentic details, and a decoder LoRA driven by a perception-oriented loss to synthesize realistic textures. Both LoRA modules are trained via alternating optimization with selective gradient propagation to preserve the pretrained latent structure.At inference, a tunable parameter α enables flexible fidelity-perception trade-offs.Experiments show Latent Harmony achieves state-of-the-art performance across UHD and standard-resolution tasks, effectively balancing efficiency, perceptual quality, and reconstruction accuracy. |
| title | Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.07961 |