# HybridFlow: Infusing Continuity into Masked Codebook for Extreme Low-Bitrate Image Compression arXiv: https://arxiv.org/abs/2404.13372 ยท HTML: https://mlsanity.com/paper/2404.13372/ ## Key facts - Cited by 14 papers in the map (data through 14 Oct 2026). - Builds on 26 of its 42 references that are in the map. - First posted on arXiv 20 Apr 2024. ## Builds on (most cited first, 26 of 26) - [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017) - [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022) - [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020) - [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021) - [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019) - [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021) - [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018) - [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018) - [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020) - [Towards Robust Blind Face Restoration with Codebook Lookup Transformer](https://mlsanity.com/paper/2206.11253/) (2022) - [MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis](https://mlsanity.com/paper/2211.09117/) (2022) - [Context-adaptive Entropy Model for End-to-end Optimized Image Compression](https://mlsanity.com/paper/1809.10452/) (2018) - [Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE](https://mlsanity.com/paper/2103.10022/) (2021) - [Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors](https://mlsanity.com/paper/2202.13142/) (2022) - [Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks](https://mlsanity.com/paper/1703.10114/) (2017) - [MLIC: Multi-Reference Entropy Model for Learned Image Compression](https://mlsanity.com/paper/2211.07273/) (2022) - [Improving Inference for Neural Image Compression](https://mlsanity.com/paper/2006.04240/) (2020) - [ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic](https://mlsanity.com/paper/2103.04039/) (2021) - [Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization](https://mlsanity.com/paper/2305.11718/) (2023) - [Soft then Hard: Rethinking the Quantization in Neural Image Compression](https://mlsanity.com/paper/2104.05168/) (2021) - [Transformers in Speech Processing: A Survey](https://mlsanity.com/paper/2303.11607/) (2023) - [Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation](https://mlsanity.com/paper/2305.13607/) (2023) - [Content Adaptive Latents and Decoder for Neural Image Compression](https://mlsanity.com/paper/2212.10132/) (2022) - [Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration](https://mlsanity.com/paper/2306.06513/) (2023) - [Learned Lossless Image Compression with a HyperPrior and Discretized Gaussian Mixture Likelihoods](https://mlsanity.com/paper/2002.01657/) (2020) - [Neural Image Compression Using Masked Sparse Visual Representation](https://mlsanity.com/paper/2309.11661/) (2023) ## Built on by (most cited first, 14 of 14) - [One-Step Diffusion-Based Image Compression with Semantic Distillation](https://mlsanity.com/paper/2505.16687/) (2025) - [RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion](https://mlsanity.com/paper/2410.02640/) (2024) - [DLF: Extreme Image Compression with Dual-generative Latent Fusion](https://mlsanity.com/paper/2503.01428/) (2025) - [TVC: Tokenized Video Compression with Ultra-Low Bit Rate](https://mlsanity.com/paper/2504.16953/) (2025) - [HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitrates](https://mlsanity.com/paper/2502.07160/) (2025) - [Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Textures](https://mlsanity.com/paper/2602.05213/) (2026) - [Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression](https://mlsanity.com/paper/2604.10546/) (2026) - [Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priors](https://mlsanity.com/paper/2603.15129/) (2026) - [Towards Efficient Low-rate Image Compression with Frequency-aware Diffusion Prior Refinement](https://mlsanity.com/paper/2601.10373/) (2026) - [Dual-Latent Collaborative Decoding for Fidelity-Perception Balanced Image Compression](https://mlsanity.com/paper/2605.14391/) (2026) - [Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression](https://mlsanity.com/paper/2606.01608/) (2026) - [Self-Supervised Compression and Artifact Correction for Streaming Underwater Imaging Sonar](https://mlsanity.com/paper/2511.13922/) (2025) - [Efficient Semantic Image Communication for Traffic Monitoring at the Edge](https://mlsanity.com/paper/2604.12622/) (2026) - [Recasting DiT for Extreme Image Compression with Hierarchical Visual Priors](https://mlsanity.com/paper/2610.18607/) (2026) ## Abstract (arXiv) This paper investigates the challenging problem of learned image compression (LIC) with extreme low bitrates. Previous LIC methods based on transmitting quantized continuous features often yield blurry and noisy reconstruction due to the severe quantization loss. While previous LIC methods based on learned codebooks that discretize visual space usually give poor-fidelity reconstruction due to the insufficient representation power of limited codewords in capturing faithful details. We propose a novel dual-stream framework, HyrbidFlow, which combines the continuous-feature-based and codebook-based streams to achieve both high perceptual quality and high fidelity under extreme low bitrates. The codebook-based stream benefits from the high-quality learned codebook priors to provide high quality and clarity in reconstructed images. The continuous feature stream targets at maintaining fidelity details. To achieve the ultra low bitrate, a masked token-based transformer is further proposed, where we only transmit a masked portion of codeword indices and recover the missing indices through token generation guided by information from the continuous feature stream. We also develop a bridging correction network to merge the two streams in pixel decoding for final image reconstruction, where the continuous stream features rectify biases of the codebook-based pixel decoder to impose reconstructed fidelity details. Experimental results demonstrate superior performance across several datasets under extremely low bitrates, compared with existing single-stream codebook-based or continuous-feature-based LIC methods.