AI Paper Atlas

Research map / 3D vision / Face and shape

Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image

Simon Giebenhain, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Zhe Chen, Matthias Niessner

ECCV 2026 · 3D vision › Face and shape · approach: 3D morphable face model regression · 1 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
use Pix2NPHM instead of Pixel3DMMPix2NPHM · NeRSemble SVFR posedL1 error: 1.66 -> 1.37Improved
use Pix2NPHM feed-forward only instead of SHeaPPix2NPHM · NeRSemble SVFR posedL1 error: 2.08 -> 1.55Improved
use Pix2NPHM instead of TokenFacePix2NPHM · NoWmean error: 0.95 (TokenFace) vs 1.01Hurt
use NPHM instead of FLAME as the 3DMM (ablation)Pix2NPHM · NoW validationmean error: 1.073 -> 1.016Improved
use NPHM instead of FLAME (ablation)Pix2NPHM · AffectNetemotion accuracy: 0.660 -> 0.711Improved
use geometric pre-trained ViT instead of DINOv2 on RGB (ablation)Pix2NPHM · NoW validationmean error: 1.165 -> 1.016Improved
add point-map encoder E_p alongside normal encoder (ablation)Pix2NPHM · NoW validationmean error: 1.053 -> 1.016Improved
use DINOv2 of estimated normals instead of RGB (ablation)Pix2NPHM · NoW validationmean error: 1.165 -> 1.168No clear effect
add 2D self-supervision to 3D training (ablation)Pix2NPHM · NoW validationmean error: 1.074 -> 1.016Improved
add 3D supervision to 2D training (ablation)Pix2NPHM · NoW validationmean error: 1.238 -> 1.016Improved
add test-time optimization to feed-forward (ablation)Pix2NPHM · NeRSemble SVFR posedL1 error: 1.55 -> 1.37Improved
add test-time optimization (ablation)Pix2NPHM · NeRSemble SVFR neutralL1 error: 1.57 -> 1.54Improved

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