Skip to content

Add SOTA compression techniques overview to README #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
GeorgePearse wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add SOTA compression techniques overview to README #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 23 additions & 0 deletions Readme.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,29 @@ CompressAI currently provides:

![PSNR performances plot on Kodak](assets/kodak-psnr.png)

## SOTA Techniques

### Image Compression

1. **ELIC (2022)** - State-of-the-art with:
- Uneven channel groups [16, 16, 32, 64, 192]
- Space-channel context (SCCTX)
- Non-local attention
- ResidualBottleneckBlock (1x1→3x3→1x1)
2. **Cheng2020 with Checkerboard Context** - Combines GMM attention model with checkerboard 2-pass decoding for parallelism
3. **JointAutoregressiveHierarchicalPriors (mbt2018)** - Best compression via combined hyperprior + autoregressive context

### Variable Bitrate

- **VBR models (2024)** with learnable gain parameters and quantization-reconstruction offsets

### Video Compression

- **ScaleSpaceFlow (ssf2020)** - Multi-scale Gaussian pyramid with optical flow + scale field prediction

### Context Modeling Evolution (newest = most advanced)

1. Factorized prior → 2. Hyperprior → 3. Autoregressive → 4. Checkerboard → 5. Channel groups → 6. SCCTX (ELIC)

> **Note**: Multi-GPU support is now experimental.

Expand Down
Loading