AI Paper Atlas

Research map / 3D vision / Face and shape

Shapefusion: 3D localized human diffusion models

Rolandos Alexandros Potamias, Michael Tarasiou, Stylianos Ploumpis, Stefanos Zafeiriou

ECCV 2024 · 3D vision › Face and shape · approach: Full-body avatar reconstruction

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
train a diffusion model with random region masking (inpainting-style) instead of latent-space segmentation (SD, LED)ShapeFusion · MimicMeFID (mm): 3.39 (LED) -> 0.30Improved
diffusion model instead of masked VAE (M-VAE) with the same masking technique (ablation)ShapeFusion · STARDIV (mm): 0.72 -> 0.98Improved
diffusion model instead of M-VAE (ablation)ShapeFusion · UHMFID (mm): 1.17 -> 0.53Improved
use mask-conditioned direct point manipulation instead of optimization-based fittingShapeFusion · point manipulation runtimetime (sec): ~22sec -> ~3.2secImproved
use ShapeFusion for expression editing vs NFRShapeFusion · expression editing runtimetime: 60s -> 3sImproved
add regularization to NFR to protect non-edited regionsNFR · expression editingmanipulation qualityMixed

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