paper-with-me

홈 › Papers

SDGIC: A Semantic Disambiguation-Guided Generative Image Compression Method for Ultra-Low Bitrates

2025-12-06 · Kaile Wang, Lijun He, Haisheng Fu, Haixia Bi, Fan Li arxiv

Generative image compression has recently shown impressive perceptual quality, but often suffers from semantic inconsistency at ultra-low bitrates (bpp < 0.05), limiting its reliable deployment in bandwidth-constrained scenarios such as 6G semantic communications. This inconsistency stems from incomplete guidance information, which introduces semantic ambiguity into the generation process and may lead to natural-looking but source-inconsistent content. In this work, we propose a Semantic-Disambiguation-Guided Generative Image Compression (SDGIC) framework to constrain diffusion-based reconstruction at ultra-low bitrates. Specifically, SDGIC compresses the source image into three compact and complementary guidance streams: a concise text caption for global semantics, a highly compressed image (HCI) for dense visual evidence, and Reconstruction-Aware Semantic Residual Tokens (RSRTs) for reconstruction-relevant residual semantics that remain ambiguous under the text caption and HCI conditions. The RSRTs are directly optimized toward the downstream denoising objective, enabling them to provide source-specific semantic constraints for disambiguating diffusion-based reconstruction. To inject these three guidance streams into the generation process effectively, we design a Dual-Path Conditioned Diffusion Decoder (DPCD), which uses cross-attention for semantic conditions and ControlNet residuals for dense visual guidance. Extensive experiments demonstrate that SDGIC improves semantic consistency at ultra-low bitrates while maintaining favorable perceptual quality, with a 23.4% reduction in AFINE on the CLIC2020 dataset.

📄 PDF Abstract BibTeX arXiv:2512.06344

Code (0)

등록된 구현이 없습니다.

Tasks

Image Compression

Similar Papers 제목 키워드 기반

Attribute Attention for Semantic Disambiguation in Zero-Shot Learning

2019-10-01 · ICCV 2019 10 · Yang Liu, Jishun Guo, Deng Cai, Xiaofei He

Zero-shot learning (ZSL) aims to accurately recognize unseen objects by learning mapping matrices that bridge the gap between visual information and semantic attributes. Previous works implicitly treat attributes equally…

AttributeZero-Shot Learning

Dynamically Visual Disambiguation of Keyword-based Image Search

2019-05-27 · Yazhou Yao, Zeren Sun, Fumin Shen, Li Liu 외

Due to the high cost of manual annotation, learning directly from the web has attracted broad attention. One issue that limits their performance is the problem of visual polysemy. To address this issue, we present an ada…

General ClassificationImage Retrieval

Towards Robust Visual Continual Learning with Multi-Prototype Supervision

2025-09-19 · Xiwei Liu, Yulong Li, Yichen Li, Xinlin Zhuang 외 arxiv

Language-guided supervision, which utilizes a frozen semantic target from a Pretrained Language Model (PLM), has emerged as a promising paradigm for visual Continual Learning (CL). However, relying on a single target int…

Continual Learning

Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification

2023-02-04 · Bohan Li, Xiao Xu, Xinghao Wang, Yutai Hou 외

Existing image augmentation methods consist of two categories: perturbation-based methods and generative methods. Perturbation-based methods apply pre-defined perturbations to augment an original image, but only locally …

DiversityImage Augmentationimage-classificationImage Classification+1

Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation

2019-03-28 · Hao Tang, Dan Xu, Nicu Sebe, Yan Yan

The state-of-the-art approaches in Generative Adversarial Networks (GANs) are able to learn a mapping function from one image domain to another with unpaired image data. However, these methods often produce artifacts and…

Generative Adversarial NetworkImage-to-Image TranslationTranslationUnsupervised Image-To-Image Translation