AI Paper Atlas

Research map / Image generation / Super-resolution

Exploring Resolution and Degradation Clues As Self-Supervised Signal for Low Quality Object Detection

Ziteng Cui, Yingying Zhu, Lin Gu, Guo-Jun Qi, Xiaoxiao Li, Renrui Zhang, Zenghui Zhang, Tatsuya Harada

ECCV 2022 · Image generation › Super-resolution · approach: Real-world super-resolution · 34 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 degradation-transformation training (Deg t) (ablation)CenterNet ResNet-18 · COCO-dmAP: 14.5 -> 16.8 (+2.3)Improved
add feature connection (skip links at /8 and /16) (ablation)CenterNet + Deg t · COCO-dmAP: 16.8 -> 17.5Improved
add ARRD at middle up-sampling layer (loc 2) (ablation)CenterNet + Deg t + feature connect · COCO-dmAP: 17.5 -> 18.4Improved
place ARRD at shallow layer loc 1 instead of loc 2 (ablation)AERIS · COCO-dmAP: 18.4 -> 18.2Hurt
place ARRD at final layer loc 3 instead of loc 2 (ablation)AERIS · COCO-dmAP: 18.4 -> 17.9Hurt
AERIS versus BSRGAN x2 pre-processing with Swin-T backboneCenterNet Swin-T · COCO-dAP: 20.2 -> 21.6Improved
pre-process with Restormer denoising on multi-degradation imagesCenterNet ResNet-18 · COCO-dAP: 14.5 -> 11.4Hurt
add ARRD to RetinaNet-FPN Swin-T on all FPN levels (1,2,3,4) (ablation)RetinaNet-FPN Swin-T · COCO-dAP: 21.5 -> 22.1Improved
add ARRD on FPN level 1 only (ablation)RetinaNet-FPN Swin-T · COCO-dAP: 21.5 -> 22.0Improved
fine-tune BSRGAN on multi-degradation dataBSRGAN pre-process · COCO-dAP: 16.8 -> 16.9Improved
fine-tune DBPN on multi-degradation dataDBPN pre-process · COCO-dAP: 15.0 -> 16.4Improved
train with down-sampling ratio range (1,2) instead of (1,4) (ablation)AERIS · COCO-dAP: 18.4 -> 17.8Hurt

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