AI Paper Atlas

Research map / 3D vision / Face and shape

ARAH: Animatable Volume Rendering of Articulated Human SDFs

Shaofei Wang, Katja Schwarz, Andreas Geiger, Siyu Tang

ECCV 2022 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 113 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 2 extra root-finding initializations from nearest SMPL bones (ablation)ARAH · ZJU-MoCap seq 313 novel viewsPSNR/SSIM/LPIPS: 31.6/0.973/0.050 -> 31.5/0.972/0.049No clear effect
use joint root-finding with learned forward LBS instead of backward LBS network (Ani-NeRF)ARAH · ZJU-MoCap seq 313 unseen posesLPIPS: 0.115 -> 0.092Improved
use ARAH instead of Neural Body on unseen posesARAH · ZJU-MoCap seq 315 unseen posesLPIPS: 0.152 -> 0.105Improved
model geometry as articulated SDF instead of Neural Body NeRFARAH · ZJU-MoCap seq 313 geometryChamfer distance: 1.258 -> 0.707Improved
model geometry as articulated SDF instead of Neural Body NeRFARAH · ZJU-MoCap seq 313 geometrynormal consistency: 0.700 -> 0.809Improved
use ARAH instead of Neural Body for novel view synthesis of training posesARAH · ZJU-MoCap seq 377 training posesPSNR: 28.1 -> 27.8Mixed
use ARAH instead of Neural Body on novel views of training posesARAH · ZJU-MoCap seq 313 training posesLPIPS: 0.068 -> 0.050Improved
use ARAH instead of NARF on H36M unseen poses (subject S5)ARAH · H36M unseen poses S5PSNR: 23.91 -> 22.79Hurt
use ARAH instead of Ani-N on H36M unseen posesARAH · H36M unseen poses (average)PSNR: 22.55 -> 23.42Improved
use the proposed ray sampling instead of surface rendering or uniform sampling with 64 samples (ablation)ARAH · ZJU-MoCap seq 313visual geometry artifactsImproved
use learned forward LBS instead of backward LBS network (ablation)ARAH · ZJU-MoCap seq 313visual artifactsImproved
use learned forward LBS instead of deterministic nearest-neighbor SMPL skinning weights (ablation)ARAH · ZJU-MoCap seq 313visual artifactsImproved

Later papers that compared with this method

7 later accepted papers report ARAH as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

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