AI Paper Atlas

Research map / 3D vision / Face and shape

Animatable Implicit Neural Representations for Creating Realistic Avatars From Videos

Xiaowei Zhou, Sida Peng, Zhen Xu, Junting Dong, Qianqian Wang, Shangzhan Zhang, Qing Shuai, Hujun Bao

TPAMI 2024 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 80 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 pose-dependent displacement field to SMPL blend weights (ablation)NeRF with SMPL blend weight field · Human3.6M novel posesPSNR: 23.61 -> 23.78Improved
use neural blend weight field instead of SMPL blend weights (ablation)NeRF with SMPL blend weight field · Human3.6M novel posesPSNR: 23.61 -> 23.64No clear effect
use pose-dependent displacement field instead of neural blend weight field (ablation)NeRF-NBW · Human3.6M novel posesPSNR: 23.65 -> 23.78Improved
use signed distance field instead of density field (ablation)NeRF-PDF · SyntheticHuman reconstructionP2S: 1.78 -> 0.70Improved
use signed distance field instead of density field (ablation)NeRF-PDF · Human3.6M image synthesis (novel poses)PSNR: 23.78 -> 23.67No clear effect
use VolSDF rendering instead of NeuS rendering (ablation)SDF-PDF · SyntheticHuman reconstructionP2S: 0.79 -> 0.70Improved
use bigger color head network instead of original NeRF network (ablation)NeRF-PDF · Human3.6M novel posesPSNR: 22.55 -> 23.65Improved
train on 100 frames instead of 1 frame (ablation)SDF-PDF · Human3.6M S9PSNR: 22.46 -> 24.14Improved
train on 800 frames instead of 200 frames (ablation)SDF-PDF · Human3.6M S9PSNR: 24.68 -> 24.48Hurt
train on 3 views instead of 1 view (ablation)SDF-PDF · Human3.6M S9PSNR: 24.21 -> 24.45No clear effect
use pose-dependent deformation instead of NB when trained on a single viewNB · ZJU-MoCap single view novel posesPSNR: 20.32 -> 22.98Improved
use SDF-PDF instead of NB with 4 viewsNB · ZJU-MoCap 4 views training posesPSNR: 28.15 -> 27.45Hurt

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