AI Paper Atlas

Research map / Video / Video segmentation and tracking

SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging

Lingtong Kong, Bo Li, Yike Xiong, Hao Zhang, Hong Gu, Jinwei Chen

ECCV 2024 · Video › Video segmentation and tracking · approach: Spike and neuromorphic deblurring · 38 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 selection masks M_i to the first fusion stage alongside optical flow (ablation)SAFNet first stage · Kalantari 17PSNR-mu: 33.69 -> 41.68Improved
add optical flow to the first fusion stage alongside selection masks (ablation)SAFNet first stage · Kalantari 17PSNR-mu: 40.69 -> 41.68Improved
feed merged HDR image H_m into the refinement network (ablation)SAFNet refine stage · Kalantari 17PSNR-mu: 43.87 -> 44.59Improved
feed optical flow and selection masks into the refinement network (ablation)SAFNet refine stage · Kalantari 17PSNR-mu: 43.63 -> 43.87Improved
use window partition cropping with 512 input for stage 1 and 128 for stage 2 (ablation)SAFNet · Kalantari 17PSNR-mu: 44.59 -> 44.66Improved
increase training patch size from 256 to 512SAFNet vs NHDRRNet · Challenge123accuracyMixed
coarse-to-fine fully convolutional design without attentionSAFNet · Kalantari 17 at 1500x1000running time: about 10x, 18x, 23x faster than FlexHDR, HDR-Transformer, SCTNetImproved
SAFNet vs transformer methods on Tel 23 (near-static backgrounds)SAFNet · Tel 23 testPSNR-mu: 44.93 -> 44.61 (SCTNet vs SAFNet)Hurt
SAFNet vs SCTNet on Tel 23 in linear domainSAFNet · Tel 23 testPSNR-l: 51.73 -> 51.97Improved

Later papers that compared with this method

1 later accepted paper reports SAFNet 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