ReFit: Recurrent Fitting Network for 3D Human Recovery

2023/08/22 by Yufu Wang, Kostas Daniilidis, Wang, Yufu +1 · 6 citations
Computer Science · Engineering · #3D Shape Modeling and Analysis #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition

paper · pdf · doi:10.48550/arxiv.2308.11184

openalex publication_date 2023/08/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present Recurrent Fitting (ReFit), a neural network architecture for single-image, parametric 3D human reconstruction. ReFit learns a feedback-update loop that mirrors the strategy of solving an inverse problem through optimization. At each iterative step, it reprojects keypoints from the human model to feature maps to query feedback, and uses a recurrent-based updater to adjust the model to fit the image better. Because ReFit encodes strong knowledge of the inverse problem, it is faster to train than previous regression models. At the same time, ReFit improves state-of-the-art performance on standard benchmarks. Moreover, ReFit applies to other optimization settings, such as multi-view fitting and single-view shape fitting. Project website: https://yufu-wang.github.io/refit_humans/

Cited by

• From Camera to World: A Plug-and-Play Module for Human Mesh Transformation
• QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture
• SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery
• PHD: Personalized 3D Human Body Fitting with Point Diffusion
• Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics
• Learning Efficient and Generalizable Human Representation with Human Gaussian Model

Related

• Neural Descent for Visual 3D Human Pose and Shape
• Human Body Model Fitting by Learned Gradient Descent
• SHARP: Shape-Aware Reconstruction of People in Loose Clothing
• PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop
• Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics