# Conceptual Compression via Deep Structure and Texture Synthesis

arXiv: https://arxiv.org/abs/2011.04976 · HTML: https://mlsanity.com/paper/2011.04976/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2020.

## Built on by (most cited first, 14 of 14)

- [Extreme Image Compression using Fine-tuned VQGANs](https://mlsanity.com/paper/2307.08265/) (2023)
- [Generative Latent Coding for Ultra-Low Bitrate Image Compression](https://mlsanity.com/paper/2512.20194/) (2025)
- [Generative Visual Compression: A Review](https://mlsanity.com/paper/2402.02140/) (2024)
- [Unifying Generation and Compression: Ultra-low bitrate Image Coding Via Multi-stage Transformer](https://mlsanity.com/paper/2403.03736/) (2024)
- [SMC++: Masked Learning of Unsupervised Video Semantic Compression](https://mlsanity.com/paper/2406.04765/) (2024)
- [Scalable Face Image Coding via StyleGAN Prior: Towards Compression for Human-Machine Collaborative Vision](https://mlsanity.com/paper/2312.15622/) (2023)
- [Thousand to One: Semantic Prior Modeling for Conceptual Coding](https://mlsanity.com/paper/2103.07131/) (2021)
- [Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling](https://mlsanity.com/paper/2211.06797/) (2022)
- [REQA: Coarse-to-fine Assessment of Image Quality to Alleviate the Range Effect](https://mlsanity.com/paper/2209.01760/) (2022)
- [Generative Human Video Compression with Multi-granularity Temporal Trajectory Factorization](https://mlsanity.com/paper/2410.10171/) (2024)
- [You Can Mask More For Extremely Low-Bitrate Image Compression](https://mlsanity.com/paper/2306.15561/) (2023)
- [Generative Image Coding with Diffusion Prior](https://mlsanity.com/paper/2509.13768/) (2025)
- [Hierarchical Semantic Compression for Consistent Image Semantic Restoration](https://mlsanity.com/paper/2502.16799/) (2025)
- [UniMIC: Token-Based Multimodal Interactive Coding for Human-AI Collaboration](https://mlsanity.com/paper/2509.22570/) (2025)

## Abstract (arXiv)

Existing compression methods typically focus on the removal of signal-level redundancies, while the potential and versatility of decomposing visual data into compact conceptual components still lack further study. To this end, we propose a novel conceptual compression framework that encodes visual data into compact structure and texture representations, then decodes in a deep synthesis fashion, aiming to achieve better visual reconstruction quality, flexible content manipulation, and potential support for various vision tasks. In particular, we propose to compress images by a dual-layered model consisting of two complementary visual features: 1) structure layer represented by structural maps and 2) texture layer characterized by low-dimensional deep representations. At the encoder side, the structural maps and texture representations are individually extracted and compressed, generating the compact, interpretable, inter-operable bitstreams. During the decoding stage, a hierarchical fusion GAN (HF-GAN) is proposed to learn the synthesis paradigm where the textures are rendered into the decoded structural maps, leading to high-quality reconstruction with remarkable visual realism. Extensive experiments on diverse images have demonstrated the superiority of our framework with lower bitrates, higher reconstruction quality, and increased versatility towards visual analysis and content manipulation tasks.