paper-with-me

Papers

Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration

2023-06-10 · ICCV 2023 1 · Kechun Liu, Yitong Jiang, Inchang Choi, Jinwei Gu

Recent work on discrete generative priors, in the form of codebooks, has shown exciting performance for image reconstruction and restoration, as the discrete prior space spanned by the codebooks increases the robustness against diverse image degradations. Nevertheless, these methods require separate training of codebooks for different image categories, which limits their use to specific image categories only (e.g. face, architecture, etc.), and fail to handle arbitrary natural images. In this paper, we propose AdaCode for learning image-adaptive codebooks for class-agnostic image restoration. Instead of learning a single codebook for each image category, we learn a set of basis codebooks. For a given input image, AdaCode learns a weight map with which we compute a weighted combination of these basis codebooks for adaptive image restoration. Intuitively, AdaCode is a more flexible and expressive discrete generative prior than previous work. Experimental results demonstrate that AdaCode achieves state-of-the-art performance on image reconstruction and restoration tasks, including image super-resolution and inpainting.

📄 PDF Abstract BibTeX arXiv:2306.06513

Code (0)

등록된 구현이 없습니다.

Tasks

Image ReconstructionImage RestorationImage Super-ResolutionSuper-Resolution

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

Content-Adaptive Pixel Discretization to Improve Model Robustness

2020-12-03 · Ryan Feng, Wu-chi Feng, Atul Prakash

Preprocessing defenses such as pixel discretization are appealing to remove adversarial attacks due to their simplicity. However, they have been shown to be ineffective except on simple datasets like MNIST. We hypothesiz…

model

Neural Image Compression Using Masked Sparse Visual Representation

2023-09-20 · Wei Jiang, Wei Wang, Yue Chen

We study neural image compression based on the Sparse Visual Representation (SVR), where images are embedded into a discrete latent space spanned by learned visual codebooks. By sharing codebooks with the decoder, the en…

DecoderImage Compression

Contrastive ECOC: Learning Output Codes for Adversarial Defense

2025-08-14 · Che-Yu Chou, Hung-Hsuan Chen arxiv

Although one-hot encoding is commonly used for multiclass classification, it is not always the most effective encoding mechanism. Error Correcting Output Codes (ECOC) address multiclass classification by mapping each cla…

Contrastive LearningAdversarial Defense

Image quality prediction using synthetic and natural codebooks: comparative results

2022-12-20 · Maxim Koroteev, Kirill Aistov, Valeriy Berezovskiy, Pavel Frolov

We investigate a model for image/video quality assessment based on building a set of codevectors representing in a sense some basic properties of images, similar to well-known CORNIA model. We analyze the codebook buildi…

CPUVideo Quality Assessment

Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks

2026-06-25 · Yunqi Xue, Zhijiang Li, Philip Torr, Jindong Gu arxiv

Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens. These tokens are derived from a codebo…

Image Generation