AI Paper Atlas

Research map / Image generation / Super-resolution

Rethinking Image Super Resolution from Training Data Perspectives

Go Ohtani, Ryu Tadokoro, Ryosuke Yamada, Yuki M Asano, Iro Laina, Christian Rupprecht, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka, Yoshimitsu Aoki

ECCV 2024 · Image generation › Super-resolution · approach: Real-world super-resolution · 6 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
train SR models on DiverSeg-I (low-resolution filtered ImageNet) instead of DF2KHAT · Urban100 x4PSNR (dB): 27.93 -> 28.51Improved
train on DiverSeg-I instead of DF2KRCAN · Urban100 x4PSNR (dB): 26.73 -> 27.03Improved
train on DiverSeg-I instead of DF2KMSRResNet · Urban100 x4PSNR (dB): 26.23 -> 26.31Improved
train on DiverSeg instead of ImageNet pretraining followed by DF2K fine-tuningHAT · Urban100 x4PSNR (dB): 28.37 -> 28.51Improved
filter by SAM segment count instead of blockiness (ablation)HAT on ImageNet-1k subset · Urban100 x4PSNR (dB): 28.39 -> 28.51Improved
use segmentation-based rather than detection-based filtering (ablation)HAT on ImageNet-1k subset · Urban100 x4PSNR (dB): 28.44 -> 28.51Improved
apply segment threshold theta=100 versus no filtering (ablation)HAT on ImageNet-1k · Urban100 x4PSNR (dB): 28.41 -> 28.51Improved
raise segment threshold from 100 to 150 (ablation)HAT on ImageNet-1k · Urban100 x4PSNR (dB): 28.51 -> 28.36Hurt
train on JPEG-compressed DF2K (quality 50) instead of HR (ablation)HAT · Urban100 x4PSNR (dB): 27.93 -> 25.04Hurt
apply object-based filtering to LSDIR (ablation)HAT · Urban100 x4PSNR (dB): 28.45 -> 28.53Improved
reduce blockiness threshold from 30 to 10 (ablation)HAT on ImageNet-1k · Urban100 x4PSNR (dB): 28.43 -> 28.41No clear effect
train on Places365 (low estimated quality) instead of ImageNet-1k or PASS (ablation)HAT · learning curvesPSNRHurt

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