Wavefront Parallelization for Efficient Learned Image Compression
Autoregressive context models are foundational for learned image compression,but they suffer from slow serial inference. Existing acceleration methods such as checkerboard context require architectural changes and retraining, thus are inapplicable to pre-trained models. We propose a completely training-free inference-time acceleration algorithm inspired by wavefront parallelism in video coding standards. Our method reorganizes inference into an optimal ``staggered'' wavefront order, minimizing sequential steps while maintaining exact autoregressive dependencies. Experimental results show our a
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “Wavefront Parallelization for Efficient Learned Image Compre” ≈ “Tongyi-MAI/Z-Image-Turbo””
- FuzzyOverlapping authors or contributors · 62%Zeyi-Lin/HivisionIDPhotos →
“Shared author/contributor keys: lin”
- FuzzyOverlapping authors or contributors · 62%hiyouga/LlamaFactory →
“Shared author/contributor keys: lin”
- LinkedLinked via arxiv author · 85%Shimon Murai →
“Wavefront Parallelization for Efficient Learned Image Compression”
- LinkedLinked via arxiv author · 85%Fangzheng Lin →
“Wavefront Parallelization for Efficient Learned Image Compression”
- LinkedLinked via arxiv author · 85%Kasidis Arunruangsirilert →
“Wavefront Parallelization for Efficient Learned Image Compression”
- LinkedLinked via arxiv author · 85%Jiro Katto →
“Wavefront Parallelization for Efficient Learned Image Compression”