AI Paper Atlas

Research map / 3D vision / Face and shape

Toward Realistic Single-View 3D Object Reconstruction With Unsupervised Learning From Multiple Images

Long-Nhat Ho, Anh Tuan Tran, Quynh Phung, Minh Hoai

ICCV 2021 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 7 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 multi-view cross-view consistency training to LeSym (ablation)LeSym · BFMMAD: 16.51 -> 15.73Improved
add multi-view training to LeSym (ablation)LeSym · BFMSIDE (x10^-2): 0.793 -> 0.728Improved
add albedo loss to LeSym (ablation)LeSym · BFMMAD: 16.51 -> 16.35Improved
add albedo loss to LeSym (ablation)LeSym · BFMSIDE (x10^-2): 0.793 -> 0.899Hurt
add albedo loss on top of multi-view (ablation)LeMul · BFMMAD: 15.73 -> 15.49Improved
add albedo loss on top of multi-view (ablation)LeMul · BFMSIDE (x10^-2): 0.728 -> 0.834Hurt
replace LeSym with LeMulunsupervised 3D face reconstruction · BFMMAD: 16.51 -> 15.49Improved
replace LeSym with LeMulunsupervised 3D face reconstruction · BFM face regionSIDE: 0.00564 -> 0.00534Improved
replace LeSym with LeMulunsupervised 3D face reconstruction · User survey CASIAselection rate (%): 20.86 -> 79.14Improved
replace LeSym with LeMulunsupervised 3D face reconstruction · User survey CatFacesselection rate (%): 47.03 -> 52.97No clear effect

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