AI Paper Atlas

Research map / Detection and segmentation / CNN features

4D Light Field Superpixel and Segmentation

Hao Zhu, Qi Zhang, Qing Wang

CVPR 2017 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 41 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 LFSP segmentation instead of SLIC and LSCLight-field superpixel segmentation · HCI synthetic light-field datasetsboundary recallImproved
Use LFSP segmentation instead of SLIC and LSCLight-field superpixel segmentation · HCI synthetic light-field datasetsunder-segmentation errorImproved
Use LFSP segmentation instead of SLIC and LSCLight-field superpixel segmentation · HCI synthetic light-field datasetsachievable segmentation accuracyImproved
Use LFSP segmentation instead of SLIC and LSCLight-field superpixel segmentation · Real Lytro light-field scenesboundary adherenceImproved
Add BCD optimization to the initial LFSP segmentation (ablation)LFSP · HCI synthetic light-field datasetsboundary recallImproved
Add BCD optimization to the initial LFSP segmentation (ablation)LFSP · HCI synthetic light-field datasetsunder-segmentation errorImproved
Add BCD optimization to the initial LFSP segmentation (ablation)LFSP · HCI synthetic light-field datasetsachievable segmentation accuracyImproved
Use the disparity map alone for segmentation instead of the full LFSP method (ablation)LFSP · HCI synthetic light-field datasetsboundary recallHurt
Use the disparity map alone for segmentation instead of the full LFSP method (ablation)LFSP · HCI synthetic light-field datasetsunder-segmentation errorHurt
Use the disparity map alone for segmentation instead of the full LFSP method (ablation)LFSP · HCI synthetic light-field datasetsachievable segmentation accuracyHurt
Refocus the light field before segmentationLFSP · HCI synthetic light-field datasets at different refocus levelsLFSP self-similarity: smaller than 1 pixelNo clear effect

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