AI Paper Atlas

Research map / 3D vision / Face and shape

Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction

Pol Caselles, Eduard Ramon, Jaime García, Gil Triginer, Francesc Moreno-Noguer

TPAMI 2025 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction

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 progressive masking and fine-tune geometry decoder (ablation)H3D-Net · H3DS ablation (23 scenes, 1 view)face surface error (mm): 1.97 -> 2.17Hurt
split geometry into deformation field plus reference SDF (ablation)H3D-Net + progressive masking · H3DS ablation (23 scenes, 1 view)face surface error (mm): 2.17 -> 1.86Improved
add joint shape and appearance prior (SA-SM) (ablation)H3D-Net + deformation field + reference SDF · H3DS ablation (23 scenes, 1 view)face surface error (mm): 1.86 -> 1.46Improved
add joint shape and appearance prior (SA-SM) (ablation)H3D-Net + deformation field + reference SDF · H3DS ablation (23 scenes, 1 view)head surface error (mm): 13.40 -> 14.16Hurt
add progressive masking (ablation)H3D-Net · H3DS ablation (23 scenes, 4 views)face surface error (mm): 1.49 -> 1.54Hurt
split geometry into deformation field plus reference SDF (ablation)H3D-Net + progressive masking · H3DS ablation (23 scenes, 4 views)head surface error (mm): 10.61 -> 9.00Improved
add joint shape and appearance prior (SA-SM) (ablation)H3D-Net + deformation field + reference SDF · H3DS ablation (23 scenes, 4 views)face surface error (mm): 1.38 -> 1.29Improved
add selective sampling (ablation)SIRA++ without cache · H3DS 2.0 (3 views, test time)test time: 379s -> 275sImproved
add dynamic SDF caching (ablation)SIRA++ without selective sampling · H3DS 2.0 (3 views, test time)test time: 379s -> 232sImproved
add both selective sampling and caching (ablation)SIRA++ · H3DS 2.0 (3 views, test time)test time: 379s -> 191sImproved
add shape and appearance prior versus H3D-NetH3D-Net · H3DS 2.0 (1 view vs 3 views) mean errorface surface error (mm): 1.44 -> 1.18Improved
add camera pose noise sigma 0.04 (ablation)H3D-Net vs SIRA++ · H3DS 3 views, camera noisehead surface error (mm): 13.36 vs 11.84Mixed

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