Pose-free 3D Gaussian splatting via shape-ray estimation

While generalizable 3D Gaussian splatting enables efficient, high-quality rendering of unseen scenes, it heavily depends on precise camera poses for accurate geometry. In real-world scenarios, obtaining accurate poses is challenging, leading to noisy pose estimates and geometric misalignments. To address this, we introduce SHARE, a pose-free, feed-forward Gaussian splatting framework that overcomes these ambiguities by joint shape and camera rays estimation. Instead of relying on explicit 3D transformations, SHARE builds a pose-aware canonical volume representation that seamlessly integrates multi-view information, reducing misalignment caused by inaccurate pose estimates. Additionally, anchor-aligned Gaussian prediction enhances scene reconstruction by refining local geometry around coarse anchors, allowing for more precise Gaussian placement. Extensive experiments on diverse real-world datasets show that our method achieves robust performance in pose-free generalizable Gaussian splatting.

@article{na2025_2505.22978,
  title={ Pose-free 3D Gaussian splatting via shape-ray estimation },
  author={ Youngju Na and Taeyeon Kim and Jumin Lee and Kyu Beom Han and Woo Jae Kim and Sung-eui Yoon },
  journal={arXiv preprint arXiv:2505.22978},
  year={ 2025 }
}