AI Paper Atlas

Research map / Image generation / Image restoration

Learned Bi-Resolution Image Coding using Generalized Octave Convolutions

Mohammad Akbari, Jie Liang, Jingning Han, Chengjie Tu

AAAI 2021 · Image generation › Image restoration · approach: Learned image compression · 16 citations (OpenAlex)

Read the paper

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
Allocate 75% of latent channels to the half-resolution LR maps instead of 50% (ablation)Proposed bi-resolution image coding · KodakPSNR: 32.35 -> 31.35Hurt
Move activation layers out of GoConv/GoTConv instead of applying them to internal feature maps (ablation)Proposed bi-resolution image coding · KodakPSNR: 32.35 -> 32.08Hurt
Use GoConv/GoTConv only for the core auto-encoder, rather than for both core and hyper auto-encoders (ablation)Proposed bi-resolution image coding · KodakPSNR: 32.35 -> 31.86Hurt
Replace GoConv/GoTConv with original octave convolutions using fixed pooling and interpolation (ablation)Proposed bi-resolution image coding · KodakPSNR: 32.35 -> 28.92; ≈3.43dB higherHurt

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