AI Paper Atlas

Research map / Image generation / Image restoration

EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation

Nikolai Körber, Eduard Kromer, Andreas Siebert, Sascha Hauke, Daniel Mueller-Gritschneder, Björn Schuller

ECCV 2024 · Image generation › Image restoration · approach: Perceptual diffusion image compression · 13 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
replace concat conditioning with pixel-wise projection in OASIS discriminator (ablation)OASIS · Cityscapes (0.092bpp)FID: 16.50 -> 13.54Improved
replace concat conditioning with projection in U-Net discriminator (ablation)U-Net discriminator · Cityscapes (0.092bpp)FID: 87.02 -> 30.80Improved
pre-train the OASIS discriminator with DeepLab2 (ablation)OASIS · Cityscapes (0.092bpp)FID: 15.30 -> 9.75Improved
use weight norm instead of spectral norm (ablation)OASIS (pre-trained) · Cityscapes (0.092bpp)FID: 9.75 -> 7.96Improved
weight norm vs layer norm (ablation)OASIS discriminator · Cityscapes (0.092bpp)FID: 9.00 -> 7.96Improved
add distortion term d to OASIS-C objective (ablation)OASIS-C · Cityscapes (0.092bpp)PSNR / FID: 29.97 -> 32.24 PSNR; 7.74 -> 6.36 FIDImproved
use stronger segmentation network (DeepLabV3+) as discriminator (ablation)OASIS · Cityscapes (0.092bpp)FID: 16.50 -> 20.61Hurt
add focal frequency loss to pixel-level discriminators (ablation)OASIS and U-Net · Cityscapes (0.092bpp)FID: 15.93 vs 16.50 (OASIS)No clear effect
add focal frequency loss to PatchGAN (ablation)PatchGAN · Cityscapes (0.092bpp)FID: 112.29 -> 40.64Improved
class-frequency pixel weighting instead of instance-size weighting (ablation)OASIS · Cityscapes (0.092bpp)FID: 15.30 -> 15.56No clear effect
replace PatchGAN with OASIS-C discriminator (HiFiC backbone, HiFiC-lo)HiFiC · CLIC 2020 / low bit rangeFID: up to 2 FID points, +0.2dB PSNRImproved
replace PatchGAN with OASIS-C discriminator (HiFiC-hi)HiFiC · high bit-rateFID/PSNRHurt

Later papers that compared with this method

1 later accepted paper reports EGIC as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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