AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Learned Image Compression with Hierarchical Progressive Context Modeling

Yuqi Li, Haotian Zhang, Li Li, Dong Liu

ICCV 2025 · Architectures and efficiency › Attention and transformers · approach: Block-sparse attention kernels · 23 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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 changedWhereMeasuredEffect
add hierarchical context extraction (ablation)HPCM-Base · KodakBD-Rate / kMACs per pixel: 1.07% -> 0.00%; 1107.48 -> 918.57 kMACs/pixelImproved
add progressive context fusion (ablation)HPCM-Base · KodakBD-Rate: 4.71% -> 0.00%Improved
use cross-attention with C_i instead of entropy parameter state psi_i as progressive context (ablation)HPCM-Base · KodakBD-Rate: 1.17% -> 0.00%Improved
increase coding steps at largest scale from 3 to 6 (ablation)HPCM-Base · KodakBD-Rate: 2.39% -> 0.00%; 663.90 -> 918.57 kMACs/pixelImproved
increase coding steps at largest scale from 6 to 12 (ablation)HPCM-Base · KodakBD-Rate: 0.00% -> -2.55%; 918.57 -> 1427.91 kMACs/pixelImproved
use 2 coding steps instead of 4 at smallest scale (ablation)HPCM-Base · KodakBD-Rate: 0.35% -> 0.00%No clear effect
add third hierarchical stage over two stages (ablation)HPCM-Base · KodakBD-Rate: 0.35% -> 0.00%Improved
add fourth hierarchical stage (ablation)HPCM-Base · KodakBD-Rate: 0.00% -> 0.18%No clear effect
use non-shared parameters across scales (ablation)HPCM-Base · Kodakparams / BD-Rate: 68.50 -> 189.99 M params; BD-Rate -0.15%No clear effect
use HPCM entropy model instead of CHARM with same transformHPCM-Base · KodakPSNR BD-Rate: 0.86% -> -15.31%Improved
use HPCM entropy model instead of DCVC-DC intra with same transformHPCM-Base · KodakPSNR BD-Rate: -9.18% -> -15.31%Improved
use HPCM-Large instead of HPCM-Base (deeper transform and entropy networks)HPCM · TecnickPSNR BD-Rate: -18.16% -> -22.20%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy