AI Paper Atlas

Research map / 3D vision / 3D generation

FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads

Weijie Lyu, Yi Zhou, Ming-Hsuan Yang, Zhixin Shu

ICCV 2025 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 19 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 input view reconstruction to multi-view diffusion training (ablation)FaceLift · CafcaArcFace distance: 0.2367 -> 0.1573Improved
add input view reconstruction to multi-view diffusion training (ablation)FaceLift · CafcaDreamSim: 0.1438 -> 0.1096Improved
add input view reconstruction to multi-view diffusion training (ablation)FaceLift · CafcaPSNR: 16.02 -> 16.61Improved
add multi-view attention (ablation)FaceLift · CafcaDreamSim: 0.1552 -> 0.1096Improved
add multi-view attention (ablation)FaceLift · CafcaArcFace distance: 0.2126 -> 0.1573Improved
replace LGM input views with FaceLift multi-view diffusion outputsLGM · CafcaArcFace distance: 0.2557 -> 0.1767Improved
replace LGM input views with FaceLift multi-view diffusion outputsLGM · CafcaPSNR: 16.52 -> 14.13Hurt
replace LGM input views with FaceLift multi-view diffusion outputsLGM · Ava-256PSNR: 14.05 -> 15.24Improved
replace LGM reconstructor with FaceLift transformer Gaussian reconstructorOur MV + LGM · CafcaDreamSim: 0.1282 -> 0.1096Improved
fine-tune LGM on synthetic head dataLGM · Cafcavisual qualityHurt
use six views instead of four views (ablation)FaceLift reconstructor · in-the-wild imagesvisual qualityImproved
use eight views instead of six views (ablation)FaceLift · in-the-wild imagesvisual qualityNo clear effect

Later papers that compared with this method

3 later accepted papers report FaceLift as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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