AI Paper Atlas

Research map / Image generation / Image restoration

Cassic: Towards Content-Adaptive State-Space Models for Learned Image Compression

Shiyu Qin, Jinpeng Wang, Yimin Zhou, Bin Chen, Tianci Luo, Baoyi An, Tao Dai, Shu-Tao Xia, Yaowei Wang

ICCV 2025 · Image generation › Image restoration · approach: Learned image compression · 3 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 CASS on the encoder side instead of 2DSS (ablation)Cassic nonlinear transform · KodakBD-rate: 2.67%Improved
add CASS on the decoder side instead of 2DSS (ablation)Cassic nonlinear transform · KodakBD-rate: 4.91%Improved
add CASS on both sides instead of 2DSS (ablation)Cassic nonlinear transform · KodakBD-rate: 6.15%Improved
add CASS on both sides instead of 2DSS (ablation)Cassic nonlinear transform · CLIC Professional ValidationBD-rate: 7.21%Improved
unfold high-value positions first in CASS rather than inverse order (ablation)Cassic CASS · KodakBD-rate: 1.34%Improved
add CASS in entropy model instead of four-directional scanning (ablation)Cassic entropy model · KodakBD-rate: 1.79%Improved
use CA-VSSB entropy model instead of Mixed (SWAtten) block (ablation)Cassic entropy model · KodakBD-rate: 2.39%Improved
use CA-VSSB entropy model instead of CCA (NAF) block (ablation)Cassic entropy model · KodakBD-rate: 4.27%Improved
use Cassic instead of MambaVCMamba-based image compression · KodakBD-rate / latency: 1.49% BD-rate gain; latency 282 -> 261 msImproved
use Cassic instead of CCA (CNN)image compression · KodakBD-rate / latency: 2.17% BD-rate gain; latency 201 -> 261 msMixed
use Cassic instead of MLIC++image compression · CLIC Professional ValidationBD-rate: 0.9%Mixed

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