AI Paper Atlas

Research map / Image generation / Image restoration

Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection Removal

Jie Yang, Dong Gong, Lingqiao Liu, Qinfeng Shi

ECCV 2018 · Image generation › Image restoration · approach: Dehazing and deraining · 188 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 reflection estimator H to vanilla generator (ablation)Vanilla G0 · Synthetic reflection test (500 images)PSNR: 22.10 -> 22.30Improved
add background estimator G1 to form full bidirectional unit (ablation)Vanilla G0 + H · Synthetic reflection test (500 images)PSNR: 22.30 -> 23.11Improved
make the vanilla generator deeper instead of adding the bidirectional unit (ablation)Vanilla G0 · Synthetic reflection test (500 images)PSNR: 22.10 -> 22.16Improved
train jointly end-to-end instead of greedy module-wise training (ablation)BDN · Synthetic reflection test (500 images)PSNR: 20.82 -> 23.11Improved
train jointly from scratch instead of greedy training plus fine-tuning (ablation)BDN · Synthetic reflection test (500 images)PSNR: 22.43 -> 23.11Improved
add adversarial loss (ablation)BDN · Synthetic reflection test (500 images)PSNR: 23.06 -> 23.11No clear effect
add adversarial loss (ablation)BDN · Synthetic reflection test (500 images)SSIM: 0.833 -> 0.835No clear effect
use BDN instead of Fan et al. when trained on our synthetic dataBDN · Our synthetic datasetPSNR: 20.03 -> 23.11Improved
use BDN instead of Fan et al. when trained on the dataset of Fan et al.BDN · Synthetic dataset of Fan et al.PSNR: 18.29 -> 20.82Improved
use BDN instead of Fan et al. on real SIR dataBDN · SIR dataset, PostcardPSNR: 21.0829 -> 20.4076Hurt
use BDN instead of Fan et al. on real SIR dataBDN · SIR dataset, Solid objectsPSNR: 23.5324 -> 22.7076Hurt
use BDN instead of Fan et al. on real SIR dataBDN · SIR dataset, Wild scenesPSNR: 22.0618 -> 22.1082Improved

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