AI Paper Atlas

Research map / 3D vision / Face and shape

Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos

Ayşegül Dündar, Kevin J. Shih, Animesh Garg, Robert Pottorff, Andrew Tao, Bryan Catanzaro

TPAMI 2021 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 27 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 foreground-background factorized rendering (ablation)landmark model (temp) · Human3.6Mlandmark error: 3.07 -> 2.73Improved
add foreground-background factorized rendering (ablation)landmark model (temp,tps) · Human3.6Mlandmark error: 2.86 -> 2.73Improved
add foreground-background factorized rendering (ablation)landmark model (temp) · BBC Posekeypoint accuracy: 73.3% -> 78.8%Improved
add foreground-background factorized rendering (ablation)landmark model (tps) · MAFLlandmark error: 4.34 -> 2.76Improved
add predicted blending masks instead of direct addition of fg and bg (ablation)Ours (No Mask) · MAFLlandmark error: 2.88 -> 2.76Improved
add TPS perturbation to temporal perturbation in baselineBaseline · BBC Posekeypoint accuracy: 73.3% -> 73.4%No clear effect
add TPS perturbation to temporal perturbation in baselineBaseline · Human3.6Mlandmark error: 3.07 -> 2.86Improved
add background factorization (fewer landmarks) (ablation)landmark model · BBC Poseaccuracy vs number of landmarksImproved
add foreground-background factorization to landmark model, 16 landmarks (ablation)landmark model · Human3.6Mlowest landmark containment in foreground: 0.05 -> 8.2Improved
change coordinate origin from center to top left (ablation)Ours · BBC Posekeypoint accuracy: 78.78 -> 79.16No clear effect
add factorized rendering to video prediction (ablation)landmark LSTM prediction · KTHLPIPS, SSIM, PSNRImproved
add factorized rendering to video prediction (ablation)landmark LSTM prediction · BAIRLPIPS, SSIM, PSNRImproved

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