AI Paper Atlas

Research map / 3D vision / Human pose estimation

True Self-Supervised Novel View Synthesis is Transferable

Thomas Mitchel, Hyunwoo Ryu, Vincent Sitzmann

ICLR 2026 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 11 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 transferability objective with masked augmentation vs plain autoencoding (unconstrained) (ablation)stereo-monocular XFactor · RE10K transfer testTPS AUC@20: 36.8 -> 47.2Improved
add transferability objective vs 16-dim bottleneck (ablation)stereo-monocular XFactor · RE10K transfer testTPS AUC@20: 40.6 -> 47.2Improved
add transferability objective vs 16-dim bottleneck (ablation)stereo-monocular XFactor · RE10K pose probeprobe AUC@20: 47.2 -> 54.8Improved
add SE(3) and Plucker parameterization to the stereo-monocular model (ablation)unconstrained stereo-monocular model · DL3DV transfer testTPS AUC@20: 39.4 -> 26.4Hurt
add an extra context view to the renderer (ablation)stereo-monocular XFactor · DL3DV transfer testTPS AUC@20: 44.8 -> 25.1Hurt
add an extra context view to both pose encoder and renderer (ablation)stereo-monocular XFactor · MVImgNet transfer testTPS AUC@20: 49.3 -> 1.2Hurt
add temporal-shift corruption (+1) to training pairs (ablation)stereo-monocular XFactor · DL3DV transfer testTPS AUC@20: 44.8 -> 36.2Hurt
add shift +1 and +2 corruption to training pairs (ablation)stereo-monocular XFactor · DL3DV pose probeprobe AUC@20: 61.2 -> 47.0Hurt
replace pose-preserving augmentation objective with SimCLR (ablation)pose encoder · RE10K pose probeprobe AUC@20: 54.8 -> 3.8Hurt
replace transferability objective with VICReg (ablation)pose encoder · RE10K pose probeprobe AUC@20: 54.8 -> 0.8Hurt
XFactor vs RayZer on transferability testXFactor multi-view · RE10K transfer testTPS AUC@20: 7.6 -> 55.2Improved
XFactor vs RUST on transferability testXFactor multi-view · CO3Dv2 transfer testTPS AUC@20: 5.4 -> 31.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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