AI Paper Atlas

Research map / 3D vision / Face and shape

SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians

Liam Schoneveld, Zhe Chen, Davide Davoli, Jiapeng Tang, Saimon Terazawa, Ko Nishino, Matthias Nießner

ICCV 2025 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 6 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 perceptual loss (ablation)photometric-only SHeaP · NoW validationmedian distance (mm): 1.09 -> 1.06Improved
add identity perceptual loss (ablation)SHeaP with perceptual loss · NoW validationmedian distance (mm): 1.06 -> 0.99Improved
add normals+depth coupling loss (ablation)SHeaP without densify/prune · NoW validationmedian distance (mm): 0.99 -> 0.96Improved
add normals+depth coupling loss (ablation)full SHeaP minus coupling · NoW validationmedian distance (mm): 0.98 -> 0.93Improved
add densification and pruning (ablation)SHeaP with ID loss and coupling · NoW validationmedian distance (mm): 0.96 -> 0.93Improved
enable graph convolution edges (ablation)SHeaP with MLP ResNet · NoW validationmedian distance (mm): 0.98 -> 0.93Improved
add densify/prune and normals+depth together (ablation)SHeaP with perceptual loss only · NoW validationmedian distance (mm): 1.06 -> 1.03Improved
add ID loss to perceptual+densify+coupling (ablation)SHeaP · NoW validationmedian distance (mm): 1.03 -> 0.93Improved
add ID loss (ablation)SHeaP with perceptual and densify/coupling · NoW validationmean distance (mm): 1.25 -> 1.16Improved
replace mesh rendering with 2D Gaussians (ablation)DECA-style mesh-rendering baseline · NoW validationmedian distance (mm): 1.18 -> 1.09Improved

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