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

TL;DR

SHARE introduces a pose-free Gaussian splatting method that jointly estimates shape and camera rays, enabling robust 3D scene reconstruction without relying on accurate camera poses, thus improving real-world applicability.

Contribution

The paper presents a novel pose-free Gaussian splatting framework that jointly estimates shape and camera rays, reducing dependence on precise camera poses for high-quality 3D rendering.

Findings

Achieves robust scene reconstruction without accurate camera poses

Outperforms existing methods on diverse real-world datasets

Enhances local geometry refinement through anchor-aligned prediction

Abstract

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. Code is avilable at https://github.com/youngju-na/SHARE