AI Paper Atlas

Research map / 3D vision / Face and shape

Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks

Junyuan Xie, Ross Girshick, Ali Farhadi

ECCV 2016 · 3D vision › Face and shape · approach: Generative textures for 3D humans · 422 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 lower-level feature side branches (multi-level upsampled features) (ablation)Deep3D · 3D movie test setMAE: 8.24 -> 6.87Improved
train end-to-end directly on stereo pairs instead of on block-matching disparity maps (ablation)Deep3D · 3D movie test setMAE: 7.29 -> 6.87Improved
add the disparity representation with differentiable selection layer instead of direct regression (ablation)Deep3D · 3D movie test setMAE: 7.01 -> 6.87Improved
use 5 consecutive RGB frames as input instead of a single frame (ablation)Deep3D · 3D movie test setMAE: 6.87 -> 6.81Improved
add 5 optical flow frames to a single RGB frame input (ablation)Deep3D · 3D movie test setMAE: 6.87 -> 6.86No clear effect
use Deep3D instead of Eigen et al. depth plus DIBR (fixed B and f)2D-to-3D conversion · 3D movie test setMAE: 7.75 -> 6.87Improved
use Deep3D instead of Eigen et al. depth plus DIBR (oracle focus plane)2D-to-3D conversion · 3D movie test set (oracle)MAE: 6.31 -> 5.47Improved
use Deep3D instead of Eigen et al. + Oracle in pairwise human judgments2D-to-3D conversion · Human studypreference rate (%): 66.08% preferred Deep3D over Eigen et al. + Oracle (33.92% the reverse)Improved
use Deep3D instead of Global Disparity in pairwise human judgments2D-to-3D conversion · Human studypreference rate (%): 74.58% preferred Deep3D over Global Disparity (25.42% the reverse)Improved

Later papers that compared with this method

8 later accepted papers report Deep3D as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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