Research map / Architectures and efficiency / RNNs and normalization
A Spatial RNN Codec for End-to-End Image Compression
Chaoyi Lin, Jiabao Yao, Fangdong Chen, Li Wang
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use block-based recurrent processing instead of a fully convolutional network (ablation) | Spatial RNN Codec · Kodak | rate-distortion performance | Improved |
| use HRNN to pass information across adjacent blocks (ablation) | Spatial RNN Codec · Kodak | rate-distortion performance | Improved |
| use HRNN instead of parallelizable BRNN (ablation) | Spatial RNN Codec · RGB Kodak | encoding and decoding time: 8.719 -> 27.214 ms encoding; 7.495 -> 34.549 ms decoding | Hurt |
| reduce BRNN block size from 128×128 to 64×64 (ablation) | Spatial RNN Codec · Kodak | rate-distortion performance | Hurt |
| reduce BRNN block size from 128×128 to 64×64 (ablation) | Spatial RNN Codec · RGB Kodak | encoding and decoding time: 8.719 -> 10.304 ms encoding; 7.495 -> 11.355 ms decoding | Hurt |
| add adaptive quantization and joint hyperpriors instead of a single hyperprior without adaptive quantization (ablation) | Spatial RNN Codec · Kodak | rate-distortion performance | Mixed |
| use the Spatial RNN Codec instead of HM16.14 | image compression · Kodak | BD-Rate: -26.73% | Improved |
Closest papers by meaning
- Improved Lossy Image Compression With Priming and Spatially Adaptive Bit Rates for Recurrent Networks (CVPR 2018 · similarity 0.89)
- Full Resolution Image Compression With Recurrent Neural Networks (CVPR 2017 · similarity 0.88)
- Neural Inter-Frame Compression for Video Coding (ICCV 2019 · similarity 0.86)
- Computationally-Efficient Neural Image Compression with Shallow Decoders (ICCV 2023 · similarity 0.86)
- DVC: An End-To-End Deep Video Compression Framework (CVPR 2019 · similarity 0.86)
- GLIC: General Format Learned Image Compression (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
