AI Paper Atlas

Research map / 3D vision / Face and shape

PaMIR: Parametric Model-Conditioned Implicit Representation for Image-Based Human Reconstruction

Zerong Zheng, Tao Yu, Yebin Liu, Qionghai Dai

TPAMI 2021 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 336 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 depth-ambiguity-aware loss with predicted SMPL (ablation)PaMIR · TwindomP2S (cm): 1.81 -> 1.60Improved
train with predicted SMPL plus DAAL instead of ground-truth SMPL (ablation)PaMIR · TwindomP2S (cm): 1.71 -> 1.60Improved
add body reference optimization at inference (ablation)PaMIR · TwindomP2S (cm): 1.60 -> 1.52Improved
add body reference optimization (SMPL pose accuracy) (ablation)PaMIR · BUFFMPJPE (cm): 2.65 -> 2.49Improved
add body reference optimization (SMPL pose accuracy) (ablation)PaMIR · TwindomMPJPE (cm): 2.85 -> 2.74Improved
fuse features from more input views (1 to 4) (ablation)PaMIR multi-image · multi-view normal reprojectionNormal reprojection error: 0.161 -> 0.135Improved
replace PIFu implicit function with SMPL-conditioned implicit functionPaMIR · BUFFP2S (cm): 1.93 -> 1.52Improved
replace PIFu implicit function with SMPL-conditioned implicit functionPaMIR · TwindomP2S (cm): 2.34 -> 1.80Improved
use ground-truth SMPL at test time instead of predictedPaMIR · BUFFP2S (cm): 1.52 -> 0.709Improved

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