AI Paper Atlas

Research map / 3D vision / Face and shape

Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the Wild

Seunguk Do, Minwoo Huh, Joonghyuk Shin, Jaesik Park

ICLR 2026 · 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
post-train PSHuman with DrPose on DrPose15KPSHuman · MixamoRPChamfer Distance: 137.2814 -> 126.5312Improved
post-train PSHuman with DrPose on DrPose15KPSHuman · THuman2.1-testChamfer Distance: 52.9643 -> 42.0529Improved
post-train PSHuman with DrPose on DrPose15KPSHuman · CustomHumans-testChamfer Distance: 52.2187 -> 44.1326Improved
post-train PSHuman with DrPose on DrPose15KPSHuman · THuman2.1-testPSNR: 18.3880 -> 20.8594Improved
post-train PSHuman with DrPose on DrPose15KPSHuman · MixamoRPNormal Consistency: 0.5876 -> 0.5998Improved
post-train Era3D* with DrPose on DrPose15KEra3D* · MixamoRPChamfer Distance: 150.0118 -> 126.0622Improved
post-train Era3D* with DrPose on DrPose15KEra3D* · THuman2.1-testPSNR: 17.7662 -> 20.3563Improved
use PSHuman instead of Era3D as base model for DrPose (ablation)DrPose · THuman2.1-test / CustomHumans-test / MixamoRPCD, NC, PSNR: CD 41.1770 vs 42.0529 (THuman2.1)No clear effect
add DrPose15K pose data (1.73x larger joint std than THuman2.1) (ablation)I2MV diffusion · pose diversitystandard deviation of joint positions: 1.73x larger std vs THuman2.1Improved
add KL divergence regularization to reward fine-tuning (ablation)DrPose · reward fine-tuningimage quality / reward hackingImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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