AI Paper Atlas

Research map / 3D vision / Face and shape

TotalSelfScan: Learning Full-body Avatars from Self-Portrait Videos of Faces, Hands, and Bodies

Junting Dong, Qi Fang, Yudong Guo, Sida Peng, Qing Shuai, Xiaowei Zhou, Hujun Bao

NeurIPS 2022 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 0 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 multi-part networks instead of a single network with the same parameter count (ablation)TotalSelfScan · SynTotalHuman head reconstructionP2S (cm): 1.03 -> 0.59Improved
use multi-part networks instead of a single network (ablation)TotalSelfScan · SynTotalHuman hands reconstructionP2S (cm): 1.25 -> 0.55Improved
use multi-part networks instead of a single network (ablation)TotalSelfScan · SynTotalHuman total reconstructionP2S (cm): 1.95 -> 1.84Improved
use multi-part networks instead of a single network (ablation)TotalSelfScan · SynTotalHuman total image synthesisPSNR: 25.19 -> 26.15Improved
use multi-part networks instead of a single network (ablation)TotalSelfScan · SynTotalHuman head image synthesisPSNR: 20.38 -> 22.23Improved
add non-rigid ray transformation (global view directions) (ablation)TotalSelfScan · SynTotalHuman total image synthesisPSNR: 25.43 -> 26.15Improved
add non-rigid ray transformation (ablation)TotalSelfScan · SynTotalHuman head image synthesisPSNR: 21.07 -> 22.23Improved
add non-rigid ray transformation (ablation)TotalSelfScan · SynTotalHuman hands image synthesisLPIPS: 0.085 -> 0.076Improved
refine head transformation with reconstructed surface alignment instead of FLAME-SMPLH registration only (ablation)TotalSelfScan · TotalHuman head-body alignmentqualitative alignmentImproved
add geometry composition loss Lg (ablation)TotalSelfScan · TotalHuman surface transitionqualitative smoothnessImproved
add latent code optimization and color field fusion for appearance composition (ablation)TotalSelfScan · TotalHuman appearance consistencyqualitative consistencyImproved
use proposed part-specific multi-part method instead of AniSDFTotalSelfScan vs AniSDF · SynTotalHuman head reconstructionP2S (cm): 0.76 -> 0.59Improved

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