Long-sequence result using our PF-LRM in an incremental way
Video frames thumbnail
We propose a Pose-Free Large Reconstruction Model (PF-LRM) for reconstructing a 3D object from a few unposed images even with little visual overlap, while simultaneously estimating the relative camera poses in ~1.3 seconds on a single A100 GPU. PF-LRM is a highly scalable method utilizing the self-attention blocks to exchange information between 3D object tokens and 2D image tokens; we predict a coarse point cloud for each view, and then use a differentiable Perspective-n-Point (PnP) solver to obtain camera poses. When trained on a huge amount of multi-view posed data of ~1M objects, PF-LRM shows strong cross-dataset generalization ability, and outperforms baseline methods by a large margin in terms of pose prediction accuracy and 3D reconstruction quality on various unseen evaluation datasets. We also demonstrate our model's applicability in downstream text/image-to-3D task with fast feed-forward inference.
@article{wang2023pf,
title={PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction},
author={Wang, Peng and Tan, Hao and Bi, Sai and Xu, Yinghao and Luan, Fujun and Sunkavalli, Kalyan and Wang, Wenping and Xu, Zexiang and Zhang, Kai},
journal={arXiv preprint arXiv:2311.12024},
year={2023}
}