AI Paper Atlas

Research map / 3D vision / 3D generation

View-Consistent 4D Light Field Superpixel Segmentation

Numair Khan, Qian Zhang, Lucas Kasser, Henry Stone, Min H. Kim, James Tompkin

ICCV 2019 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 25 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
use occlusion-aware EPI segmentation with all-view propagation instead of LFSP central-view propagationlight field superpixels · HCI, estimated disparityself similarity error and labels per pixelImproved
use our method instead of LFSP with ground truth disparitylight field superpixels · HCI, ground truth disparityself similarity error and labels per pixelImproved
use our method instead of k-means with ground truth disparitylight field superpixels · HCI, ground truth disparitynumber of labels per pixelHurt
use our method instead of k-means with ground truth disparitylight field superpixels · HCI, ground truth disparityself similarity errorImproved
use our method instead of LFSPlight field superpixels · HCI, sizes 15-40achievable accuracy, boundary recall, undersegmentation errorImproved
use our method instead of k-means with ground truth disparity at larger superpixel sizeslight field superpixels · HCI, large sizesaccuracy and undersegmentation errorHurt
use our method instead of k-means with ground truth disparity at small sizes (15-25)light field superpixels · HCI, sizes 15-25accuracy and undersegmentation errorNo clear effect
use our method instead of k-meanslight field superpixels · HCIboundary recallHurt
use our method instead of LFSP at small superpixel sizes (15-25)light field superpixels · HCI, sizes 15-25compactnessNo clear effect
use our method instead of LFSP at larger superpixel sizeslight field superpixels · HCI, large sizescompactnessImproved
use our method instead of k-meanslight field superpixels · HCIcompactnessImproved
use our method (3.3 minutes) instead of LFSP plus Wang disparity (about 10 minutes)light field superpixels · HCI 9x9 768x768computation time: ~8 minutes + ~2 minutes -> ~3.3 minutesImproved

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