AI Paper Atlas

Research map / Image generation / Image restoration

Learning Content-Weighted Deep Image Compression

Mu Li, Wangmeng Zuo, Shuhang Gu, Jane You, David D. Zhang

TPAMI 2020 · Image generation › Image restoration · approach: Learned image compression · 93 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 channel-wise learnt quantization (LCMQ) instead of one shared learnt quantizer (LMQ) (ablation)CWIC · Kodakquantization error (average): 1.05 -> 0.90Improved
add learnt quantization (LMQ) instead of fixed uniform levels (FMQ) (ablation)CWIC · Kodakquantization error (average): 1.97 -> 1.05Improved
use 8-level multi-valued quantization (LCMQ) instead of binarization (BIN) (ablation)CWIC · Kodakquantization error (average): 3.18 -> 0.90Improved
use LCMQ instead of BIN, LMQ or FMQ (ablation)CWIC · KodakMS-SSIM rate-distortionImproved
add importance map subnet with spatially variant bit allocation (ablation)CWIC · KodakMS-SSIM rate-distortionImproved
use TCAE or inclined TCAE instead of modified CABAC context (ablation)CWIC · Kodaklossless compression ratioImproved
use larger context (TCAE 37x37) instead of 4x5x5 context of Li et al. (ablation)CWIC · Kodaklossless compression ratioImproved
increase number of feature-map groups in inclined TCAE (1,2,4,8 for o'; 4,8,16,32 for p') (ablation)inclined TCAE · Kodakcompression ratioImproved
use inclined TCAE instead of TCAE for decoding o' (ablation)CWIC · Kodakdecoding time (s): 202.8 -> 0.923Improved
use inclined TCAE instead of TCAE for decoding p' (ablation)CWIC · Kodakdecoding time (s): 6.58 -> 0.161Improved
train with MS-SSIM loss instead of MSE lossCWIC · KodakMS-SSIM rate-distortionImproved

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