AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits

Xiaoyong Shen, Hongyun Gao, Xin Tao, Chao Zhou, Jiaya Jia

ICCV 2017 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 9 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 joint correspondence refinement to the segmentation CRF (vs updating segmentation only) (ablation)Ours · Dual-lens portrait segmentation (200 test pairs)mean IoU (%): 84.32 -> 88.33Improved
add joint segmentation refinement to the correspondence CRF (vs updating correspondence only) (ablation)Ours · Dual-lens portrait correspondence (200 test pairs)AEPE: 8.03 -> 5.29Improved
add joint segmentation refinement to the correspondence CRF (vs updating correspondence only) (ablation)Ours · Dual-lens portrait correspondence (200 test pairs)AAE: 7.45 -> 5.91Improved
add regional correspondence (vs 500 uniform constant displacement labels) (ablation)Ours · Regional correspondence studyAEPE: 6.45 -> 5.29Improved
add regional correspondence (vs 500 uniform constant displacement labels) (ablation)Ours · Regional correspondence studyrunning time (s): 186.3 -> 16.63Improved
fine-tune 2-class FCN on portrait dataFCN · Dual-lens portrait segmentation (200 test pairs)mean IoU (%): 79.51 -> 83.90Improved
fine-tune 2-class DeepLab on portrait dataDeepLab · Dual-lens portrait segmentation (200 test pairs)mean IoU (%): 80.09 -> 84.01Improved
fine-tune 2-class CRFasRNN on portrait dataCRFasRNN · Dual-lens portrait segmentation (200 test pairs)mean IoU (%): 80.23 -> 84.19Improved
update segmentation only with the CRF on top of fine-tuned FCNFCN-portrait · Dual-lens portrait segmentation (200 test pairs)mean IoU (%): 83.90 -> 84.32No clear effect
replace fully connected CRF pairwise term with MRF neighbourhood term (ablation)Ours · Qualitative arm region examplevisual qualityHurt

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