AI Paper Atlas

Research map / 3D vision / Face and shape

MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos

Yushuo Chen, Zerong Zheng, Zhe Li, Chao Xu, Yebin Liu

ECCV 2024 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 35 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 hybrid mesh-plus-implicit representation with radiance rendering instead of prior avatar methodsMeshAvatar (radiance) · AvatarReX training frame reconstructionPSNR: 28.4015 -> 28.9939Improved
replace radiance rendering with physics-based rendering (ablation)MeshAvatar · AvatarReX novel pose synthesisPSNR: 26.6194 -> 26.8526 PSNR; LPIPS 0.0657 -> 0.0693Mixed
add pseudo normal supervision (ablation)MeshAvatar · SyntheticHuman++Normal error (degrees): 19.37 -> 13.44Improved
add pseudo normal supervision (ablation)MeshAvatar · SyntheticHuman++ relightingPSNR: 26.92 -> 27.19Improved
add pseudo normal supervision (ablation)MeshAvatar · SyntheticHuman++ visibilityPSNR: 20.36 -> 22.30Improved
combine shadow-aware PBR with pseudo normal supervision (ablation)MeshAvatar · training frame geometry (qualitative)geometry qualityImproved
use MeshAvatar without normal prior against AvatarReXMeshAvatar (w/o normal) · AvatarReX novel pose synthesisLPIPS / SSIM: LPIPS 0.0684 -> 0.0687No clear effect
compare MeshAvatar normal accuracy to Xu et al. on synthetic dataMeshAvatar · SyntheticHuman++Normal error (degrees): 12.44 -> 13.44Hurt

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