AI Paper Atlas

Research map / Image generation / Image restoration

Single Image Deraining: A Comprehensive Benchmark Analysis

Siyuan Li, Iago Breno Araujo, Wenqi Ren, Zhangyang Wang, Eric K. Tokuda, Roberto Hirata Junior, Roberto Cesar-Junior, Jiawan Zhang, Xiaojie Guo, Xiaochun Cao

CVPR 2019 · Image generation › Image restoration · approach: Dehazing and deraining · 364 citations (OpenAlex)

Check 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
Use a rain-streak-specific derainer rather than the degraded inputSynthetic rain-streak images · Rain streak (S)PSNR: 25.95 -> 29.39Improved
Use DeRaindrop, specialized for raindrops, rather than the degraded inputSynthetic raindrop images · Raindrop (S)PSNR: 25.40 -> 31.57Improved
Apply deraining before detectionYOLO-V3 on RID · RIDmAP: 27.84 -> 23.75Hurt
Apply deraining before detectionYOLO-V3 on RIS · RISmAP: 23.27 -> 18.71Hurt
Use a rain-streak detection-and-removal strategySynthetic rain-streak deraining · Rain streak (S)PSNRImproved
Use rain-focused attention or masks to guide removalRain-streak and raindrop deraining · Rain streak (S), Raindrop (S)PSNRImproved
Use a model with fewer physical priors and rain-type assumptionsCGAN · Rain and mist (R)NIQEImproved
Use patch-based GMM rather than DeRaindropHuman-rated raindrop removal · Raindrops (R), subjective surveysubjective score: 0.80 -> 1.14Improved
Use GAN-based CGAN rather than other tested derainersHuman-rated rain-streak removal · Rain streak (R), subjective surveysubjective score: 1.15 -> 1.26Improved
Use DID-MDN rather than CGANHuman-rated rain-and-mist removal · Rain and mist (R), subjective surveysubjective score: 1.22 -> 1.40Improved
Use deraining as a preprocessing step for object detectionExisting derainers on RID and RIS · RID and RISmAPHurt
Use no-reference IQA metrics as a substitute for human judgmentsDeraining evaluation · Real-world rainy imagessubjective quality alignmentHurt

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