mlsanityData to 7 Oct 2026

Flexible Neural Image Compression via Code Editing

arXiv 2209.09244 ↗First posted 19 Sep 2022eess.IV cs.CV cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

Neural image compression (NIC) has outperformed traditional image codecs in rate-distortion (R-D) performance. However, it usually requires a dedicated encoder-decoder pair for each point on R-D curve, which greatly hinders its practical deployment. While some recent works have enabled bitrate control via conditional coding, they impose strong prior during training and provide limited flexibility. In this paper we propose Code Editing, a highly flexible coding method for NIC based on semi-amortized inference and adaptive quantization. Our work is a new paradigm for variable bitrate NIC. Furthermore, experimental results show that our method surpasses existing variable-rate methods, and achieves ROI coding and multi-distortion trade-off with a single decoder.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 19 Sep 2022.

Builds on

29 of 40 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2018Variational image compression with a scale hyperpriorcited by 910
  4. 2016End-to-end Optimized Image Compressioncited by 673
  5. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  6. 2017The Perception-Distortion Tradeoffcited by 582
  7. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  8. 2020High-Fidelity Generative Image Compressioncited by 331
  9. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  10. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
  11. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
  12. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
17 more
  1. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 207
  2. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 193
  3. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 177
  4. 2016Full Resolution Image Compression with Recurrent Neural Networkscited by 170
  5. 2015Variable Rate Image Compression with Recurrent Neural Networkscited by 168
  6. 2018Inference Suboptimality in Variational Autoencoderscited by 131
  7. 2019Variable Rate Deep Image Compression With a Conditional Autoencodercited by 109
  8. 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 102
  9. 2018Iterative Amortized Inferencecited by 93
  10. 2017Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networkscited by 91
  11. 2018Semi-Amortized Variational Autoencoderscited by 83
  12. 2020Asymmetric Gained Deep Image Compression With Continuous Rate Adaptationcited by 83
  13. 2020Improving Inference for Neural Image Compressioncited by 81
  14. 2021Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transformcited by 56
  15. 2019Content Adaptive Optimization for Neural Image Compressioncited by 40
  16. 2021NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Resultscited by 22
  17. 2021Interpolation variable rate image compressioncited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 8; 2025: 3; 2026: 2.

19 papers.

Sort:

By area:

  1. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  2. 2024Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Modelcited by 16
  3. 2023Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compressioncited by 13
  4. 2024Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video Compressioncited by 12
  5. 2023On the Choice of Perception Loss Function for Learned Video Compressioncited by 10
  6. 2022Bit Allocation using Optimizationcited by 9
  7. 2024PSC: Posterior Sampling-Based Compressioncited by 5
  8. 2024STanH : Parametric Quantization for Variable Rate Learned Image Compressioncited by 4
  9. 2023Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compressioncited by 3
  10. 2024Robustly overfitting latents for flexible neural image compressioncited by 2
  11. 2022Correcting the Sub-optimal Bit Allocationcited by 1
  12. 2024Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compressioncited by 1
7 more
  1. 2025Bitstream Collisions in Neural Image Compression via Adversarial Perturbationscited by 1
  2. 2026TinySense: Effective CSI Compression for Scalable and Accurate Wi-Fi Sensingcited by 1
  3. 2026TextBoost: Boosting Scene Text Fidelity in Ultra-low Bitrate Image Compressioncited by 1
  4. 2024FLLIC: Functionally Lossless Image Compressioncited by 0
  5. 2024Effectiveness of learning-based image codecs on fingerprint storagecited by 0
  6. 2025UniMIC: Token-Based Multimodal Interactive Coding for Human-AI Collaborationcited by 0
  7. 2025Neural Weight Compression for Language Modelscited by 0