Skip to yearly menu bar Skip to main content

Spotlight Poster

PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction

Peng Wang · Hao Tan · Sai Bi · Yinghao Xu · Fujun Luan · Kalyan Sunkavalli · Wenping Wang · Zexiang Xu · Kai Zhang

Halle B #28
[ ] [ Project Page ]
Wed 8 May 1:45 a.m. PDT — 3:45 a.m. PDT


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 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. Our project website is at:

Chat is not available.