AI Paper Atlas

Research map / 3D vision / Face and shape

Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View Settings

Baixin Xu, Jiarui Zhang, Kwan-Yee Lin, Chen Qian, Ying He

ICCV 2023 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 10 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 displacement field in Stage 2 (ablation)Ours · PR-Senior (10 views)Chamfer distance (1e-4): 1.163 -> 0.792Improved
add displacement field in Stage 2 (ablation)Ours · PR-Young (10 views)Chamfer distance (1e-4): 1.842 -> 0.723Improved
add TV regularization on displacement (ablation)Ours · Model 619 qualitative (10 views)visual noiseImproved
two-stage training with pre-trained multi-person template instead of single-stage simultaneous learning (HF-NeuS style)Ours vs HF-NeuS · PR-Senior/PR-Young, 10 viewsreconstruction failures: HF-NeuS failed on 19 of 30 persons at 10 viewsImproved
geometry decomposition with template, deformation and displacement vs NeuSOurs · PR-Senior (10 views)Chamfer distance (1e-4): 1.795 -> 0.785Improved
increase input views to 20Ours vs baselines · PR-Senior/PR-YoungChamfer distance gap: PR-Young 20 views: 0.818 vs HF-NeuS 0.831No clear effect
proposed method vs baselines on training-view PSNROurs · PR-Senior (10 views)PSNR training views: 34.81 (HF-NeuS) vs 33.78 (Ours)Hurt
proposed method vs baselines on novel-view PSNROurs · PR-Senior (10 views)PSNR novel views: 21.24 (HF-NeuS) -> 27.89Improved
use pre-trained template on 30 identities instead of template trained on 3 new identities (ablation)Ours (unseen identities, 5 views) · Identities 552, 555, 598Chamfer distance (1e-4): 1.815 -> 1.197 (id 552)Improved

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