ReFit: Recurrent Fitting Network for 3D Human Recovery
This addresses the problem of efficient and accurate 3D human recovery from images for applications in computer vision and graphics, with incremental improvements over existing methods.
The paper tackles single-image 3D human reconstruction by introducing ReFit, a neural network that learns a feedback-update loop to solve the inverse problem, resulting in faster training and improved state-of-the-art performance on benchmarks.
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/