AI Paper Atlas

Research map / Image generation / Image restoration

Content Adaptive Latents and Decoder for Neural Image Compression

Guanbo Pan, Guo Lu, Zhihao Hu, Dong Xu

ECCV 2022 · Image generation › Image restoration · approach: Learned image compression · 26 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 content adaptive feature transformation (CAFT) to the decoder (ablation)non-context baseline · TecnickBDBR (%): -9.47Improved
add content adaptive channel dropping (CACD) to the latents (ablation)non-context baseline · TecnickBDBR (%): -1.51Improved
add CACD on top of CAFT (ablation)non-context baseline · TecnickBDBR (%): -9.47 -> -11.08Improved
combine content adaptive methods with SGA (ablation)non-context baseline · KodakBDBR (%): -15.17 -> -26.52Improved
combine content adaptive methods with SGA (ablation)non-context baseline · TecnickBDBR (%): -18.72 -> -28.51Improved
use content adaptive methods alone instead of SGA's encoder-side updatingnon-context baseline · KodakBDBR (%): -15.17 -> -11.51Hurt
add content adaptive methods to video codec DVC*DVC* · HEVC Class CPSNR: about 0.1 dB at middle bit-rate, about 0.3 dB at other bit-ratesImproved

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