AI Paper Atlas

Research map / 3D vision / Face and shape

OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction

Zeyu CAI, Yuliang Xiu, renke wang, Zhijing Shao, Xiaoben Li, YU Siyuan, Chao Xu, Yang Liu, Baigui Sun, Jian Yang, zhenyu zhang

ECCV 2026 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 1 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 scale predictor for scale-normalized inputs (ablation)OmniFit · 4D-DRESS (scale-normalized)V2V (cm): 1.120 -> 0.651Improved
add scale predictor for scale-normalized inputs (ablation)OmniFit · 4D-DRESS (scale-normalized)MPJPE (cm): 1.172 -> 0.709Improved
add image adapter with front-view RGB (ablation)OmniFit · 4D-DRESSV2V (cm): 0.589 -> 0.539Improved
add image adapter with front-view RGB (ablation)OmniFit · 4D-DRESSMPJPE (cm): 0.662 -> 0.622Improved
use 180/120/300 landmark split instead of 120/120/360 hands/head/body (ablation)OmniFit · 4D-DRESSV2V (cm): 0.637 -> 0.589Improved
use 180/120/300 landmark split instead of 300/120/180 (ablation)OmniFit · 4D-DRESSV2V (cm): 0.655 -> 0.589Improved
increase landmarks from 100 to 600 (ablation)OmniFit · 4D-DRESSV2V (cm): 0.637 -> 0.589Improved
increase landmarks from 100 to 600 (ablation)OmniFit · 4D-DRESSGFLOPs: 23.82 -> 93.38Hurt
increase input points from 5000 to 15000 (ablation)OmniFit · 4D-DRESSV2V (cm): 0.589 -> 0.452Improved
use DINOv2 instead of Sapiens as image encoder (ablation)OmniFit adapter · 4D-DRESSV2V (cm): 0.589 -> 0.539Improved
train on unified dataset (Ours*) instead of 4D-DRESS onlyOmniFit · THuman2.1V2V (cm): 1.768 -> 1.338Improved
train adapter on unified dataset (Adapter*)OmniFit adapter · THuman2.1V2V (cm): 1.767 -> 0.835Improved

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