AI Paper Atlas

Research map / Image generation / Super-resolution

Towards Practical and Efficient High-Resolution HDR Deghosting with CNN

K. Ram Prabhakar, Susmit Agrawal, Durgesh Kumar Singh, Balraj Ashwath, R. Venkatesh Babu

ECCV 2020 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 74 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 Nmc motion segmentation together with Ng weight-map fusion for the guide image (ablation)guide image Hg · UCSD testPSNR-T: 37.24 -> 41.56Improved
replace simple difference-based motion detection with learned Nmc before Ng (ablation)guide image Hg · UCSD testPSNR-T: 39.06 -> 41.56Improved
add Ng learned weight maps instead of triangle fusion after Nmc (ablation)guide image Hg · UCSD testPSNR-T: 37.98 -> 41.56Improved
add optical flow alignment of low-resolution inputs to Nf (ablation)Nf · UCSD test (d=1)PSNR-T: 41.16 -> 42.82Improved
use optical-flow aligned inputs instead of motion-compensated sequence for Nf (ablation)Nf · UCSD test (d=1)PSNR-T: 41.54 -> 42.82Improved
add XSDC blocks instead of ten vanilla convolutional layers (ablation)Nf · UCSD testPSNR-T: 41.08 -> 42.82Improved
extend SDC to XSDC (three consecutive convs, 1x1 aggregation) (ablation)Nf · UCSD testPSNR-T: 41.94 -> 42.34Improved
add dense connections among XSDC blocks (ablation)Nf · UCSD testPSNR-T: 42.34 -> 42.82Improved
use XSDC instead of ResNet18 backbone (ablation)Nf · UCSD testPSNR-T: 42.45 -> 42.82Improved
add BGU low-resolution processing (d=8) instead of full-resolution processing (d=1) (ablation)Ours · Kalantari UCSD testPSNR-T: 43.08 -> 42.82Hurt
use low-resolution processing with BGU for high-resolution imagesOurs · 16 MP imagesrunning time: 11 seconds for 16 MP vs 42 seconds for 1 MP (Kalantari17)Improved

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