paper-with-me

Papers

A Novel Framework for Image-to-image Translation and Image Compression

2021-11-25 · Fei Yang, Yaxing Wang, Luis Herranz, Yongmei Cheng, Mikhail Mozerov

Data-driven paradigms using machine learning are becoming ubiquitous in image processing and communications. In particular, image-to-image (I2I) translation is a generic and widely used approach to image processing problems, such as image synthesis, style transfer, and image restoration. At the same time, neural image compression has emerged as a data-driven alternative to traditional coding approaches in visual communications. In this paper, we study the combination of these two paradigms into a joint I2I compression and translation framework, focusing on multi-domain image synthesis. We first propose distributed I2I translation by integrating quantization and entropy coding into an I2I translation framework (i.e. I2Icodec). In practice, the image compression functionality (i.e. autoencoding) is also desirable, requiring to deploy alongside I2Icodec a regular image codec. Thus, we further propose a unified framework that allows both translation and autoencoding capabilities in a single codec. Adaptive residual blocks conditioned on the translation/compression mode provide flexible adaptation to the desired functionality. The experiments show promising results in both I2I translation and image compression using a single model.

📄 PDF Abstract BibTeX arXiv:2111.13105

Code (0)

등록된 구현이 없습니다.

Tasks

Image CompressionImage GenerationImage RestorationImage-to-Image TranslationQuantizationStyle TransferTranslation

Similar Papers 제목 키워드 기반

Cross Modal Compression: Towards Human-comprehensible Semantic Compression

2022-09-06 · Jiguo Li, Chuanmin Jia, Xinfeng Zhang, Siwei Ma 외

Traditional image/video compression aims to reduce the transmission/storage cost with signal fidelity as high as possible. However, with the increasing demand for machine analysis and semantic monitoring in recent years,…

Feature CompressionSemantic CompressionVideo Compression

Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reduction

2023-08-15 · ICCV 2023 1 · Chaeyeon Chung, Yeojeong Park, Seunghwan Choi, Munkhsoyol Ganbat 외

Video-to-video translation aims to generate video frames of a target domain from an input video. Despite its usefulness, the existing networks require enormous computations, necessitating their model compression for wide…

Computational EfficiencyModel CompressionTranslation

Knowledge Distillation for Image Restoration : Simultaneous Learning from Degraded and Clean Images

2025-01-16 · Yongheng Zhang, Danfeng Yan

Model compression through knowledge distillation has seen extensive application in classification and segmentation tasks. However, its potential in image-to-image translation, particularly in image restoration, remains u…

DecoderImage ReconstructionImage RestorationImage-to-Image Translation+2

Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction

2018-10-18 · Bolun Zheng, Yaowu Chen, Xiang Tian, Fan Zhou 외

Several dual-domain convolutional neural network-based methods show outstanding performance in reducing image compression artifacts. However, they suffer from handling color images because the compression processes for g…

Color Image Compression Artifact ReductionImage CompressionImage Compression Artifact ReductionJPEG Artifact Correction+2

Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks

2022-03-03 · CVPR 2022 1 · Chanyong Jung, Gihyun Kwon, Jong Chul Ye

Recently, contrastive learning-based image translation methods have been proposed, which contrasts different spatial locations to enhance the spatial correspondence. However, the methods often ignore the diverse semantic…

Contrastive LearningImage-to-Image TranslationRelationTranslation