mlsanityData to 7 Oct 2026

Theoretical Bound-Guided Hierarchical VAE for Neural Image Codecs

arXiv 2403.18535 ↗First posted 27 Mar 2024eess.IV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Recent studies reveal a significant theoretical link between variational autoencoders (VAEs) and rate-distortion theory, notably in utilizing VAEs to estimate the theoretical upper bound of the information rate-distortion function of images. Such estimated theoretical bounds substantially exceed the performance of existing neural image codecs (NICs). To narrow this gap, we propose a theoretical bound-guided hierarchical VAE (BG-VAE) for NIC. The proposed BG-VAE leverages the theoretical bound to guide the NIC model towards enhanced performance. We implement the BG-VAE using Hierarchical VAEs and demonstrate its effectiveness through extensive experiments. Along with advanced neural network blocks, we provide a versatile, variable-rate NIC that outperforms existing methods when considering both rate-distortion performance and computational complexity. The code is available at BG-VAE.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 21 of its 27 references that are in the map. First posted on arXiv 27 Mar 2024.

Builds on

21 of 27 references.

References · 21

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2022A ConvNet for the 2020scited by 3,545
  4. 2020Knowledge Distillation: A Surveycited by 1,578
  5. 2018Variational image compression with a scale hyperpriorcited by 910
  6. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  7. 2016End-to-end Optimized Image Compressioncited by 673
  8. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  9. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  10. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  11. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  12. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
9 more
  1. 2023Learned Image Compression with Mixed Transformer-CNN Architecturescited by 205
  2. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 141
  3. 2022Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practicecited by 136
  4. 2023QARV: Quantization-Aware ResNet VAE for Lossy Image Compressioncited by 30
  5. 2022Improved Feature Distillation via Projector Ensemblecited by 27
  6. 2022High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregationcited by 16
  7. 2021Towards Empirical Sandwich Bounds on the Rate-Distortion Functioncited by 13
  8. 2023Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillationcited by 11
  9. 2024Another Way to the Top: Exploit Contextual Clustering in Learned Image Codingcited by 6

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025Balanced Rate-Distortion Optimization in Learned Image Compressioncited by 5
  2. 2025Accelerating Learned Image Compression Through Modeling Neural Training Dynamicscited by 1
  3. 2025OpenDCVCs: A PyTorch Open Source Implementation and Performance Evaluation of the DCVC series Video Codecscited by 1