AI Paper Atlas

Research map / 3D vision / Depth and stereo

Stereoscopic Neural Style Transfer

Dongdong Chen, Lu Yuan, Jing Liao, Nenghai Yu, Gang Hua

CVPR 2018 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 119 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 symmetric bidirectional disparity consistency lossstereoscopic style transfer · stereoscopic imagesdisparity consistencyImproved
jointly process the left and right views symmetrically rather than stylizing sequentiallyoptimization-based stereoscopic style transfer · stereoscopic imagestexture continuity near occlusion boundariesImproved
use bidirectional rather than single-directional disparity and occlusion prediction (ablation)DispOccNet · MPI Sintel cleannon-occluded EPE: 4.66 -> 4.16Improved
use bidirectional rather than single-directional disparity and occlusion prediction (ablation)DispOccNet · FlyingThings3D testnon-occluded EPE: 1.69 -> 1.68No clear effect
remove disparity deviation penalty in occluded regions (ablation)DispOccNet · MPI Sintel cleannon-occluded EPE: 5.43 -> 4.16Improved
remove disparity deviation penalty in occluded regions (ablation)DispOccNet · FlyingThings3D testnon-occluded EPE: 1.99 -> 1.68Improved
predict occlusion masks directly rather than derive them by post bidirectional consistency checkDispOccNet · FlyingThings3D testocclusion-mask F-score: 0.805 -> 0.887Improved
add DispOccNet and the disparity consistency training to the style networkstereoscopic style transfer · FlyingThings3D test, Candydisparity loss: 0.0624 -> 0.0474Improved
add DispOccNet and the disparity consistency training to the style networkstereoscopic style transfer · FlyingThings3D test, La_musedisparity loss: 0.0403 -> 0.0301Improved
add DispOccNet and the disparity consistency training to the style networkstereoscopic style transfer · FlyingThings3D test, Mosaicdisparity loss: 0.0668 -> 0.0559Improved
add DispOccNet and the disparity consistency training to the style networkstereoscopic style transfer · FlyingThings3D test, Udniedisparity loss: 0.0379 -> 0.0285Improved
replace symmetric bidirectional feature composition with asymmetric single-directional composition (ablation)stereoscopic style transfer · FlyingThings3D test, Candydisparity loss: 0.0474 -> 0.0481Hurt

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