AI Paper Atlas

Research map / Image generation / GANs

Unsupervised Segmentation Incorporating Shape Prior via Generative Adversarial Networks

Dahye Kim, Byung-Woo Hong

ICCV 2021 · Image generation › GANs · approach: GAN-based image manipulation · 5 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 shape prior GAN on top of intrinsic image segmentation (ablation)Intrinsic segmentation · LSUN carIoU: 0.3250 -> 0.6340Improved
add shape prior GAN on top of intrinsic image segmentation (ablation)Intrinsic segmentation · LSUN boatIoU: 0.2348 -> 0.4901Improved
add shape prior GAN on top of intrinsic image segmentation (ablation)Intrinsic segmentation · LSUN airplaneIoU: 0.2307 -> 0.4714Improved
add shape prior GAN on top of intrinsic image segmentation (ablation)Intrinsic segmentation · LSUN chairIoU: 0.3683 -> 0.4776Improved
add intrinsic image decomposition before segmentation with shape prior (ablation)Original + shape · LSUN carIoU: 0.6303 -> 0.6340Improved
add intrinsic image decomposition before segmentation with shape prior (ablation)Original + shape · LSUN boatIoU: 0.4756 -> 0.4901Improved
add intrinsic image decomposition before segmentation with shape prior (ablation)Original + shape · LSUN chairIoU: 0.4824 -> 0.4776Hurt
add intrinsic image decomposition without shape prior (ablation)Original only · LSUN carIoU: 0.3126 -> 0.3250Improved
add intrinsic image decomposition without shape prior (ablation)Original only · LSUN boatIoU: 0.2002 -> 0.2348Improved
add shape prior and intrinsic decomposition vs strongest baseline GrabCutFull model · LSUN chairIoU: 0.5127 -> 0.4776Hurt
add intrinsic decomposition on heavy occlusion with strong bias (ablation)Original + shape · Synthetic squares (occlusion 80%, bias std 0.4)IoU: 0.3911 -> 0.7649Improved
add shape prior on intrinsic images with heavy occlusion (ablation)Intrinsic segmentation · Synthetic squares (occlusion 80%, bias std 0.4)IoU: 0.3168 -> 0.7649Improved

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